Use TCP on RDMA connection failure

(To prevent excessive load on etcd during outages)

.gitea/workflows/buildenv.Dockerfile

@@ -22,7 +22,7 @@ RUN apt-get update
 RUN apt-get -y install etcd qemu-system-x86 qemu-block-extra qemu-utils fio libasan5 \
     liburing1 liburing-dev libgoogle-perftools-dev devscripts libjerasure-dev cmake libibverbs-dev libisal-dev
 RUN apt-get -y build-dep fio qemu=`dpkg -s qemu-system-x86|grep ^Version:|awk '{print $2}'`
-RUN apt-get -y install jq lp-solve sudo nfs-common
+RUN apt-get update && apt-get -y install jq lp-solve sudo nfs-common fdisk parted
 RUN apt-get --download-only source fio qemu=`dpkg -s qemu-system-x86|grep ^Version:|awk '{print $2}'`
 
 RUN set -ex; \

.gitea/workflows/test.yml

@@ -16,6 +16,7 @@ env:
   BUILDENV_IMAGE: git.yourcmc.ru/vitalif/vitastor/buildenv
   TEST_IMAGE: git.yourcmc.ru/vitalif/vitastor/test
   OSD_ARGS: '--etcd_quick_timeout 2000'
+  USE_RAMDISK: 1
 
 concurrency:
   group: ci-${{ github.ref }}
@@ -197,6 +198,24 @@ jobs:
           echo ""
         done
 
+  test_etcd_fail_antietcd:
+    runs-on: ubuntu-latest
+    needs: build
+    container: ${{env.TEST_IMAGE}}:${{github.sha}}
+    steps:
+    - name: Run test
+      id: test
+      timeout-minutes: 10
+      run: ANTIETCD=1 /root/vitastor/tests/test_etcd_fail.sh
+    - name: Print logs
+      if: always() && steps.test.outcome == 'failure'
+      run: |
+        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
+          echo "-------- $i --------"
+          cat $i
+          echo ""
+        done
+
   test_interrupted_rebalance:
     runs-on: ubuntu-latest
     needs: build
@@ -269,6 +288,24 @@ jobs:
           echo ""
         done
 
+  test_create_halfhost:
+    runs-on: ubuntu-latest
+    needs: build
+    container: ${{env.TEST_IMAGE}}:${{github.sha}}
+    steps:
+    - name: Run test
+      id: test
+      timeout-minutes: 3
+      run: /root/vitastor/tests/test_create_halfhost.sh
+    - name: Print logs
+      if: always() && steps.test.outcome == 'failure'
+      run: |
+        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
+          echo "-------- $i --------"
+          cat $i
+          echo ""
+        done
+
   test_failure_domain:
     runs-on: ubuntu-latest
     needs: build
@@ -377,6 +414,24 @@ jobs:
           echo ""
         done
 
+  test_rm_degraded:
+    runs-on: ubuntu-latest
+    needs: build
+    container: ${{env.TEST_IMAGE}}:${{github.sha}}
+    steps:
+    - name: Run test
+      id: test
+      timeout-minutes: 3
+      run: /root/vitastor/tests/test_rm_degraded.sh
+    - name: Print logs
+      if: always() && steps.test.outcome == 'failure'
+      run: |
+        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
+          echo "-------- $i --------"
+          cat $i
+          echo ""
+        done
+
   test_snapshot_chain:
     runs-on: ubuntu-latest
     needs: build
@@ -539,6 +594,24 @@ jobs:
           echo ""
         done
 
+  test_dd:
+    runs-on: ubuntu-latest
+    needs: build
+    container: ${{env.TEST_IMAGE}}:${{github.sha}}
+    steps:
+    - name: Run test
+      id: test
+      timeout-minutes: 3
+      run: /root/vitastor/tests/test_dd.sh
+    - name: Print logs
+      if: always() && steps.test.outcome == 'failure'
+      run: |
+        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
+          echo "-------- $i --------"
+          cat $i
+          echo ""
+        done
+
   test_root_node:
     runs-on: ubuntu-latest
     needs: build
@@ -665,6 +738,24 @@ jobs:
           echo ""
         done
 
+  test_heal_antietcd:
+    runs-on: ubuntu-latest
+    needs: build
+    container: ${{env.TEST_IMAGE}}:${{github.sha}}
+    steps:
+    - name: Run test
+      id: test
+      timeout-minutes: 10
+      run: ANTIETCD=1 /root/vitastor/tests/test_heal.sh
+    - name: Print logs
+      if: always() && steps.test.outcome == 'failure'
+      run: |
+        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
+          echo "-------- $i --------"
+          cat $i
+          echo ""
+        done
+
   test_heal_csum_32k_dmj:
     runs-on: ubuntu-latest
     needs: build
@@ -773,6 +864,60 @@ jobs:
           echo ""
         done
 
+  test_resize:
+    runs-on: ubuntu-latest
+    needs: build
+    container: ${{env.TEST_IMAGE}}:${{github.sha}}
+    steps:
+    - name: Run test
+      id: test
+      timeout-minutes: 3
+      run: /root/vitastor/tests/test_resize.sh
+    - name: Print logs
+      if: always() && steps.test.outcome == 'failure'
+      run: |
+        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
+          echo "-------- $i --------"
+          cat $i
+          echo ""
+        done
+
+  test_resize_auto:
+    runs-on: ubuntu-latest
+    needs: build
+    container: ${{env.TEST_IMAGE}}:${{github.sha}}
+    steps:
+    - name: Run test
+      id: test
+      timeout-minutes: 3
+      run: /root/vitastor/tests/test_resize_auto.sh
+    - name: Print logs
+      if: always() && steps.test.outcome == 'failure'
+      run: |
+        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
+          echo "-------- $i --------"
+          cat $i
+          echo ""
+        done
+
+  test_snapshot_pool2:
+    runs-on: ubuntu-latest
+    needs: build
+    container: ${{env.TEST_IMAGE}}:${{github.sha}}
+    steps:
+    - name: Run test
+      id: test
+      timeout-minutes: 3
+      run: /root/vitastor/tests/test_snapshot_pool2.sh
+    - name: Print logs
+      if: always() && steps.test.outcome == 'failure'
+      run: |
+        for i in /root/vitastor/testdata/*.log /root/vitastor/testdata/*.txt; do
+          echo "-------- $i --------"
+          cat $i
+          echo ""
+        done
+
   test_osd_tags:
     runs-on: ubuntu-latest
     needs: build

.gitea/workflows/tests-to-yaml.pl

@@ -34,6 +34,10 @@ for my $line (<>)
             {
                 $test_name .= '_imm';
             }
+            elsif ($1 eq 'ANTIETCD')
+            {
+                $test_name .= '_antietcd';
+            }
             else
             {
                 $test_name .= '_'.lc($1).'_'.$2;

CMakeLists.txt

@@ -2,6 +2,6 @@ cmake_minimum_required(VERSION 2.8.12)
 
 project(vitastor)
 
-set(VERSION "1.7.1")
+set(VITASTOR_VERSION "2.0.0")
 
 add_subdirectory(src)

README-ru.md

@@ -1,4 +1,4 @@
-## Vitastor
+# Vitastor
 
 [Read English version](README.md)
 
@@ -6,7 +6,7 @@
 
 Вернём былую скорость кластерному блочному хранилищу!
 
-Vitastor - распределённая блочная и файловая SDS (программная СХД), прямой аналог Ceph RBD и CephFS,
+Vitastor - распределённая блочная, файловая и объектная SDS (программная СХД), прямой аналог Ceph RBD, CephFS и RGW,
 а также внутренних СХД популярных облачных провайдеров. Однако, в отличие от них, Vitastor
 быстрый и при этом простой. Только пока маленький :-).
 
@@ -19,10 +19,10 @@ Vitastor нацелен в первую очередь на SSD и SSD+HDD кл
 TCP и RDMA и на хорошем железе может достигать задержки 4 КБ чтения и записи на уровне ~0.1 мс,
 что примерно в 10 раз быстрее, чем Ceph и другие популярные программные СХД.
 
-Vitastor поддерживает QEMU-драйвер, протоколы NBD и NFS, драйверы OpenStack, Proxmox, Kubernetes.
+Vitastor поддерживает QEMU-драйвер, протоколы NBD и NFS, драйверы OpenStack, OpenNebula, Proxmox, Kubernetes.
 Другие драйверы могут также быть легко реализованы.
 
-Подробности смотрите в документации по ссылкам ниже.
+Подробности смотрите в документации по ссылкам. Можете начать отсюда: [Быстрый старт](docs/intro/quickstart.ru.md).
 
 ## Презентации и записи докладов
 
@@ -41,16 +41,19 @@ Vitastor поддерживает QEMU-драйвер, протоколы NBD и
   - [Автор и лицензия](docs/intro/author.ru.md)
 - Установка
   - [Пакеты](docs/installation/packages.ru.md)
+  - [Docker](docs/installation/docker.ru.md)
   - [Proxmox](docs/installation/proxmox.ru.md)
+  - [OpenNebula](docs/installation/opennebula.ru.md)
   - [OpenStack](docs/installation/openstack.ru.md)
   - [Kubernetes CSI](docs/installation/kubernetes.ru.md)
+  - [S3](docs/installation/s3.ru.md)
   - [Сборка из исходных кодов](docs/installation/source.ru.md)
 - Конфигурация
   - [Обзор](docs/config.ru.md)
   - Параметры
     - [Общие](docs/config/common.ru.md)
     - [Сетевые](docs/config/network.ru.md)
-    - [Клиентский код](docs/config/client.en.md)
+    - [Клиентский код](docs/config/client.ru.md)
     - [Глобальные дисковые параметры](docs/config/layout-cluster.ru.md)
     - [Дисковые параметры OSD](docs/config/layout-osd.ru.md)
     - [Прочие параметры OSD](docs/config/osd.ru.md)

README.md

@@ -6,7 +6,7 @@
 
 Make Clustered Block Storage Fast Again.
 
-Vitastor is a distributed block and file SDS, direct replacement of Ceph RBD and CephFS,
+Vitastor is a distributed block, file and object SDS, direct replacement of Ceph RBD, CephFS and RGW,
 and also internal SDS's of public clouds. However, in contrast to them, Vitastor is fast
 and simple at the same time. The only thing is it's slightly young :-).
 
@@ -19,10 +19,10 @@ supports TCP and RDMA and may achieve 4 KB read and write latency as low as ~0.1
 with proper hardware which is ~10 times faster than other popular SDS's like Ceph
 or internal systems of public clouds.
 
-Vitastor supports QEMU, NBD, NFS protocols, OpenStack, Proxmox, Kubernetes drivers.
+Vitastor supports QEMU, NBD, NFS protocols, OpenStack, OpenNebula, Proxmox, Kubernetes drivers.
 More drivers may be created easily.
 
-Read more details below in the documentation.
+Read more details in the documentation. You can start from here: [Quick Start](docs/intro/quickstart.en.md).
 
 ## Talks and presentations
 
@@ -41,9 +41,12 @@ Read more details below in the documentation.
   - [Author and license](docs/intro/author.en.md)
 - Installation
   - [Packages](docs/installation/packages.en.md)
+  - [Docker](docs/installation/docker.en.md)
   - [Proxmox](docs/installation/proxmox.en.md)
+  - [OpenNebula](docs/installation/opennebula.en.md)
   - [OpenStack](docs/installation/openstack.en.md)
   - [Kubernetes CSI](docs/installation/kubernetes.en.md)
+  - [S3](docs/installation/s3.en.md)
   - [Building from Source](docs/installation/source.en.md)
 - Configuration
   - [Overview](docs/config.en.md)

csi/Dockerfile

@@ -22,6 +22,8 @@ RUN apt-get update && \
     (echo "APT::Install-Recommends false;" > /etc/apt/apt.conf) && \
     apt-get update && \
     apt-get install -y e2fsprogs xfsprogs kmod iproute2 \
+        # NFS mount dependencies
+        nfs-common netbase \
         # dependencies of qemu-storage-daemon
         libnuma1 liburing2 libglib2.0-0 libfuse3-3 libaio1 libzstd1 libnettle8 \
         libgmp10 libhogweed6 libp11-kit0 libidn2-0 libunistring2 libtasn1-6 libpcre2-8-0 libffi8 && \

csi/Makefile

@@ -1,9 +1,9 @@
-VERSION ?= v1.7.1
+VITASTOR_VERSION ?= v2.0.0
 
 all: build push
 
 build:
-	@docker build --rm -t vitalif/vitastor-csi:$(VERSION) .
+	@docker build --rm -t vitalif/vitastor-csi:$(VITASTOR_VERSION) .
 
 push:
-	@docker push vitalif/vitastor-csi:$(VERSION)
+	@docker push vitalif/vitastor-csi:$(VITASTOR_VERSION)

csi/deploy/004-csi-nodeplugin.yaml

@@ -49,7 +49,7 @@ spec:
             capabilities:
               add: ["SYS_ADMIN"]
             allowPrivilegeEscalation: true
-          image: vitalif/vitastor-csi:v1.7.1
+          image: vitalif/vitastor-csi:v2.0.0
           args:
             - "--node=$(NODE_ID)"
             - "--endpoint=$(CSI_ENDPOINT)"

csi/deploy/007-csi-provisioner.yaml

@@ -121,7 +121,7 @@ spec:
             privileged: true
             capabilities:
               add: ["SYS_ADMIN"]
-          image: vitalif/vitastor-csi:v1.7.1
+          image: vitalif/vitastor-csi:v2.0.0
           args:
             - "--node=$(NODE_ID)"
             - "--endpoint=$(CSI_ENDPOINT)"

csi/deploy/009-storage-class.yaml

@@ -9,8 +9,16 @@ metadata:
 provisioner: csi.vitastor.io
 volumeBindingMode: Immediate
 parameters:
-  etcdVolumePrefix: ""
-  poolId: "1"
+  # CSI driver can create block-based volumes and VitastorFS-based volumes
+  # only VitastorFS-based volumes and raw block volumes (without FS) support ReadWriteMany mode
+  # set this parameter to VitastorFS metadata volume name to use VitastorFS
+  # if unset, block-based volumes will be created
+  vitastorfs: ""
+  # for block-based storage classes, pool ID may be either a string (name) or a number (ID)
+  # for vitastorFS-based storage classes it must be a string - name of the default pool for FS data
+  poolId: "testpool"
+  # volume name prefix for block-based storage classes or NFS subdirectory (including /) for FS-based volumes
+  volumePrefix: ""
   # you can choose other configuration file if you have it in the config map
   # different etcd URLs and prefixes should also be put in the config
   #configPath: "/etc/vitastor/vitastor.conf"

csi/deploy/example-storage-class-fs.yaml

@@ -0,0 +1,25 @@
+---
+apiVersion: storage.k8s.io/v1
+kind: StorageClass
+metadata:
+  namespace: vitastor-system
+  name: vitastor
+  annotations:
+    storageclass.kubernetes.io/is-default-class: "true"
+provisioner: csi.vitastor.io
+volumeBindingMode: Immediate
+parameters:
+  # CSI driver can create block-based volumes and VitastorFS-based volumes
+  # only VitastorFS-based volumes and raw block volumes (without FS) support ReadWriteMany mode
+  # set this parameter to VitastorFS metadata volume name to use VitastorFS
+  # if unset, block-based volumes will be created
+  vitastorfs: "testfs"
+  # for block-based storage classes, pool ID may be either a string (name) or a number (ID)
+  # for vitastorFS-based storage classes it must be a string - name of the default pool for FS data
+  poolId: "testpool"
+  # volume name prefix for block-based storage classes or NFS subdirectory (including /) for FS-based volumes
+  volumePrefix: "k8s/"
+  # you can choose other configuration file if you have it in the config map
+  # different etcd URLs and prefixes should also be put in the config
+  #configPath: "/etc/vitastor/vitastor.conf"
+allowVolumeExpansion: true

csi/go.mod

@@ -3,10 +3,10 @@ module vitastor.io/csi
 go 1.15
 
 require (
-	github.com/container-storage-interface/spec v1.4.0
+	github.com/container-storage-interface/spec v1.8.0
 	github.com/golang/glog v0.0.0-20160126235308-23def4e6c14b
 	github.com/kubernetes-csi/csi-lib-utils v0.9.1
-	golang.org/x/net v0.0.0-20201202161906-c7110b5ffcbb
+	golang.org/x/net v0.7.0
 	golang.org/x/xerrors v0.0.0-20200804184101-5ec99f83aff1 // indirect
 	google.golang.org/grpc v1.33.1
 	google.golang.org/protobuf v1.24.0

csi/go.sum

@@ -41,8 +41,8 @@ github.com/chzyer/logex v1.1.10/go.mod h1:+Ywpsq7O8HXn0nuIou7OrIPyXbp3wmkHB+jjWR
 github.com/chzyer/readline v0.0.0-20180603132655-2972be24d48e/go.mod h1:nSuG5e5PlCu98SY8svDHJxuZscDgtXS6KTTbou5AhLI=
 github.com/chzyer/test v0.0.0-20180213035817-a1ea475d72b1/go.mod h1:Q3SI9o4m/ZMnBNeIyt5eFwwo7qiLfzFZmjNmxjkiQlU=
 github.com/container-storage-interface/spec v1.2.0/go.mod h1:6URME8mwIBbpVyZV93Ce5St17xBiQJQY67NDsuohiy4=
-github.com/container-storage-interface/spec v1.4.0 h1:ozAshSKxpJnYUfmkpZCTYyF/4MYeYlhdXbAvPvfGmkg=
-github.com/container-storage-interface/spec v1.4.0/go.mod h1:6URME8mwIBbpVyZV93Ce5St17xBiQJQY67NDsuohiy4=
+github.com/container-storage-interface/spec v1.8.0 h1:D0vhF3PLIZwlwZEf2eNbpujGCNwspwTYf2idJRJx4xI=
+github.com/container-storage-interface/spec v1.8.0/go.mod h1:ROLik+GhPslwwWRNFF1KasPzroNARibH2rfz1rkg4H0=
 github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
 github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
@@ -182,6 +182,7 @@ github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UV
 github.com/stretchr/testify v1.4.0/go.mod h1:j7eGeouHqKxXV5pUuKE4zz7dFj8WfuZ+81PSLYec5m4=
 github.com/stretchr/testify v1.5.1 h1:nOGnQDM7FYENwehXlg/kFVnos3rEvtKTjRvOWSzb6H4=
 github.com/stretchr/testify v1.5.1/go.mod h1:5W2xD1RspED5o8YsWQXVCued0rvSQ+mT+I5cxcmMvtA=
+github.com/yuin/goldmark v1.4.13/go.mod h1:6yULJ656Px+3vBD8DxQVa3kxgyrAnzto9xy5taEt/CY=
 go.opencensus.io v0.21.0/go.mod h1:mSImk1erAIZhrmZN+AvHh14ztQfjbGwt4TtuofqLduU=
 go.opencensus.io v0.22.0/go.mod h1:+kGneAE2xo2IficOXnaByMWTGM9T73dGwxeWcUqIpI8=
 go.opencensus.io v0.22.2/go.mod h1:yxeiOL68Rb0Xd1ddK5vPZ/oVn4vY4Ynel7k9FzqtOIw=
@@ -195,6 +196,7 @@ golang.org/x/crypto v0.0.0-20190605123033-f99c8df09eb5/go.mod h1:yigFU9vqHzYiE8U
 golang.org/x/crypto v0.0.0-20191011191535-87dc89f01550/go.mod h1:yigFU9vqHzYiE8UmvKecakEJjdnWj3jj499lnFckfCI=
 golang.org/x/crypto v0.0.0-20191206172530-e9b2fee46413/go.mod h1:LzIPMQfyMNhhGPhUkYOs5KpL4U8rLKemX1yGLhDgUto=
 golang.org/x/crypto v0.0.0-20200622213623-75b288015ac9/go.mod h1:LzIPMQfyMNhhGPhUkYOs5KpL4U8rLKemX1yGLhDgUto=
+golang.org/x/crypto v0.0.0-20210921155107-089bfa567519/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
 golang.org/x/exp v0.0.0-20190121172915-509febef88a4/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA=
 golang.org/x/exp v0.0.0-20190306152737-a1d7652674e8/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA=
 golang.org/x/exp v0.0.0-20190510132918-efd6b22b2522/go.mod h1:ZjyILWgesfNpC6sMxTJOJm9Kp84zZh5NQWvqDGG3Qr8=
@@ -213,6 +215,7 @@ golang.org/x/mobile v0.0.0-20190719004257-d2bd2a29d028/go.mod h1:E/iHnbuqvinMTCc
 golang.org/x/mod v0.0.0-20190513183733-4bf6d317e70e/go.mod h1:mXi4GBBbnImb6dmsKGUJ2LatrhH/nqhxcFungHvyanc=
 golang.org/x/mod v0.1.0/go.mod h1:0QHyrYULN0/3qlju5TqG8bIK38QM8yzMo5ekMj3DlcY=
 golang.org/x/mod v0.1.1-0.20191105210325-c90efee705ee/go.mod h1:QqPTAvyqsEbceGzBzNggFXnrqF1CaUcvgkdR5Ot7KZg=
+golang.org/x/mod v0.6.0-dev.0.20220419223038-86c51ed26bb4/go.mod h1:jJ57K6gSWd91VN4djpZkiMVwK6gcyfeH4XE8wZrZaV4=
 golang.org/x/net v0.0.0-20180724234803-3673e40ba225/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
 golang.org/x/net v0.0.0-20180906233101-161cd47e91fd/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
 golang.org/x/net v0.0.0-20181114220301-adae6a3d119a/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
@@ -228,8 +231,10 @@ golang.org/x/net v0.0.0-20190620200207-3b0461eec859/go.mod h1:z5CRVTTTmAJ677TzLL
 golang.org/x/net v0.0.0-20191209160850-c0dbc17a3553/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
 golang.org/x/net v0.0.0-20200324143707-d3edc9973b7e/go.mod h1:qpuaurCH72eLCgpAm/N6yyVIVM9cpaDIP3A8BGJEC5A=
 golang.org/x/net v0.0.0-20200707034311-ab3426394381/go.mod h1:/O7V0waA8r7cgGh81Ro3o1hOxt32SMVPicZroKQ2sZA=
-golang.org/x/net v0.0.0-20201202161906-c7110b5ffcbb h1:eBmm0M9fYhWpKZLjQUUKka/LtIxf46G4fxeEz5KJr9U=
-golang.org/x/net v0.0.0-20201202161906-c7110b5ffcbb/go.mod h1:sp8m0HH+o8qH0wwXwYZr8TS3Oi6o0r6Gce1SSxlDquU=
+golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg=
+golang.org/x/net v0.0.0-20220722155237-a158d28d115b/go.mod h1:XRhObCWvk6IyKnWLug+ECip1KBveYUHfp+8e9klMJ9c=
+golang.org/x/net v0.7.0 h1:rJrUqqhjsgNp7KqAIc25s9pZnjU7TUcSY7HcVZjdn1g=
+golang.org/x/net v0.7.0/go.mod h1:2Tu9+aMcznHK/AK1HMvgo6xiTLG5rD5rZLDS+rp2Bjs=
 golang.org/x/oauth2 v0.0.0-20180821212333-d2e6202438be/go.mod h1:N/0e6XlmueqKjAGxoOufVs8QHGRruUQn6yWY3a++T0U=
 golang.org/x/oauth2 v0.0.0-20190226205417-e64efc72b421/go.mod h1:gOpvHmFTYa4IltrdGE7lF6nIHvwfUNPOp7c8zoXwtLw=
 golang.org/x/oauth2 v0.0.0-20190604053449-0f29369cfe45/go.mod h1:gOpvHmFTYa4IltrdGE7lF6nIHvwfUNPOp7c8zoXwtLw=
@@ -240,6 +245,7 @@ golang.org/x/sync v0.0.0-20181221193216-37e7f081c4d4/go.mod h1:RxMgew5VJxzue5/jJ
 golang.org/x/sync v0.0.0-20190227155943-e225da77a7e6/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20190911185100-cd5d95a43a6e/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
+golang.org/x/sync v0.0.0-20220722155255-886fb9371eb4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sys v0.0.0-20180905080454-ebe1bf3edb33/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20180909124046-d0be0721c37e/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20181116152217-5ac8a444bdc5/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
@@ -259,13 +265,22 @@ golang.org/x/sys v0.0.0-20200302150141-5c8b2ff67527/go.mod h1:h1NjWce9XRLGQEsW7w
 golang.org/x/sys v0.0.0-20200323222414-85ca7c5b95cd/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20200615200032-f1bc736245b1/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20200622214017-ed371f2e16b4/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
-golang.org/x/sys v0.0.0-20200930185726-fdedc70b468f h1:+Nyd8tzPX9R7BWHguqsrbFdRx3WQ/1ib8I44HXV5yTA=
-golang.org/x/sys v0.0.0-20200930185726-fdedc70b468f/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20210615035016-665e8c7367d1/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.0.0-20220520151302-bc2c85ada10a/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.0.0-20220722155257-8c9f86f7a55f/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.5.0 h1:MUK/U/4lj1t1oPg0HfuXDN/Z1wv31ZJ/YcPiGccS4DU=
+golang.org/x/sys v0.5.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
+golang.org/x/term v0.0.0-20210927222741-03fcf44c2211/go.mod h1:jbD1KX2456YbFQfuXm/mYQcufACuNUgVhRMnK/tPxf8=
+golang.org/x/term v0.5.0/go.mod h1:jMB1sMXY+tzblOD4FWmEbocvup2/aLOaQEp7JmGp78k=
 golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
 golang.org/x/text v0.3.1-0.20180807135948-17ff2d5776d2/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
 golang.org/x/text v0.3.2/go.mod h1:bEr9sfX3Q8Zfm5fL9x+3itogRgK3+ptLWKqgva+5dAk=
-golang.org/x/text v0.3.3 h1:cokOdA+Jmi5PJGXLlLllQSgYigAEfHXJAERHVMaCc2k=
 golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
+golang.org/x/text v0.3.7/go.mod h1:u+2+/6zg+i71rQMx5EYifcz6MCKuco9NR6JIITiCfzQ=
+golang.org/x/text v0.7.0 h1:4BRB4x83lYWy72KwLD/qYDuTu7q9PjSagHvijDw7cLo=
+golang.org/x/text v0.7.0/go.mod h1:mrYo+phRRbMaCq/xk9113O4dZlRixOauAjOtrjsXDZ8=
 golang.org/x/time v0.0.0-20181108054448-85acf8d2951c/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
 golang.org/x/time v0.0.0-20190308202827-9d24e82272b4/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
 golang.org/x/time v0.0.0-20191024005414-555d28b269f0/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
@@ -286,8 +301,10 @@ golang.org/x/tools v0.0.0-20190628153133-6cdbf07be9d0/go.mod h1:/rFqwRUd4F7ZHNgw
 golang.org/x/tools v0.0.0-20190816200558-6889da9d5479/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
 golang.org/x/tools v0.0.0-20190911174233-4f2ddba30aff/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
 golang.org/x/tools v0.0.0-20191012152004-8de300cfc20a/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
+golang.org/x/tools v0.0.0-20191119224855-298f0cb1881e/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
 golang.org/x/tools v0.0.0-20191125144606-a911d9008d1f/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
 golang.org/x/tools v0.0.0-20191227053925-7b8e75db28f4/go.mod h1:TB2adYChydJhpapKDTa4BR/hXlZSLoq2Wpct/0txZ28=
+golang.org/x/tools v0.1.12/go.mod h1:hNGJHUnrk76NpqgfD5Aqm5Crs+Hm0VOH/i9J2+nxYbc=
 golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 golang.org/x/xerrors v0.0.0-20191011141410-1b5146add898/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=

csi/src/config.go

@@ -5,7 +5,7 @@ package vitastor
 
 const (
     vitastorCSIDriverName    = "csi.vitastor.io"
-    vitastorCSIDriverVersion = "1.7.1"
+    vitastorCSIDriverVersion = "2.0.0"
 )
 
 // Config struct fills the parameters of request or user input

csi/src/controllerserver.go

@@ -8,11 +8,8 @@ import (
     "encoding/json"
     "fmt"
     "strings"
-    "bytes"
-    "strconv"
     "time"
     "os"
-    "os/exec"
     "io/ioutil"
 
     "github.com/kubernetes-csi/csi-lib-utils/protosanitizer"
@@ -70,9 +67,10 @@ func GetConnectionParams(params map[string]string) (map[string]string, error)
     {
         configPath = "/etc/vitastor/vitastor.conf"
     }
-    else
+    ctxVars["configPath"] = configPath
+    if (params["vitastorfs"] != "")
     {
-        ctxVars["configPath"] = configPath
+        ctxVars["vitastorfs"] = params["vitastorfs"]
     }
     config := make(map[string]interface{})
     configFD, err := os.Open(configPath)
@@ -114,22 +112,6 @@ func GetConnectionParams(params map[string]string) (map[string]string, error)
     return ctxVars, nil
 }
 
-func system(program string, args ...string) ([]byte, []byte, error)
-{
-    klog.Infof("Running "+program+" "+strings.Join(args, " "))
-    c := exec.Command(program, args...)
-    var stdout, stderr bytes.Buffer
-    c.Stdout, c.Stderr = &stdout, &stderr
-    err := c.Run()
-    if (err != nil)
-    {
-        stdoutStr, stderrStr := string(stdout.Bytes()), string(stderr.Bytes())
-        klog.Errorf(program+" "+strings.Join(args, " ")+" failed: %s, status %s\n", stdoutStr+stderrStr, err)
-        return nil, nil, status.Error(codes.Internal, stdoutStr+stderrStr+" (status "+err.Error()+")")
-    }
-    return stdout.Bytes(), stderr.Bytes(), nil
-}
-
 func invokeCLI(ctxVars map[string]string, args []string) ([]byte, error)
 {
     if (ctxVars["configPath"] != "")
@@ -158,27 +140,57 @@ func (cs *ControllerServer) CreateVolume(ctx context.Context, req *csi.CreateVol
         return nil, status.Error(codes.InvalidArgument, "volume capabilities is a required field")
     }
 
-    etcdVolumePrefix := req.Parameters["etcdVolumePrefix"]
-    poolId, _ := strconv.ParseUint(req.Parameters["poolId"], 10, 64)
-    if (poolId == 0)
-    {
-        return nil, status.Error(codes.InvalidArgument, "poolId is missing in storage class configuration")
-    }
-
-    volName := etcdVolumePrefix + req.GetName()
-    volSize := 1 * GB
-    if capRange := req.GetCapacityRange(); capRange != nil
-    {
-        volSize = ((capRange.GetRequiredBytes() + MB - 1) / MB) * MB
-    }
-
     ctxVars, err := GetConnectionParams(req.Parameters)
     if (err != nil)
     {
         return nil, err
     }
 
-    args := []string{ "create", volName, "-s", fmt.Sprintf("%v", volSize), "--pool", fmt.Sprintf("%v", poolId) }
+    err = cs.checkCaps(volumeCapabilities, ctxVars["vitastorfs"] != "")
+    if (err != nil)
+    {
+        return nil, err
+    }
+
+    pool := req.Parameters["poolId"]
+    if (pool == "")
+    {
+        return nil, status.Error(codes.InvalidArgument, "poolId is missing in storage class configuration")
+    }
+    volumePrefix := req.Parameters["volumePrefix"]
+    if (volumePrefix == "")
+    {
+        // Old name
+        volumePrefix = req.Parameters["etcdVolumePrefix"]
+    }
+    volName := volumePrefix + req.GetName()
+    volSize := 1 * GB
+    if capRange := req.GetCapacityRange(); capRange != nil
+    {
+        volSize = ((capRange.GetRequiredBytes() + MB - 1) / MB) * MB
+    }
+
+    if (ctxVars["vitastorfs"] != "")
+    {
+        // Nothing to create, subdirectories are created during mounting
+        // FIXME: It would be cool to support quotas some day and set it here
+        if (req.VolumeContentSource.GetSnapshot() != nil)
+        {
+            return nil, status.Error(codes.InvalidArgument, "VitastorFS doesn't support snapshots")
+        }
+        ctxVars["name"] = volName
+        ctxVars["pool"] = pool
+        volumeIdJson, _ := json.Marshal(ctxVars)
+        return &csi.CreateVolumeResponse{
+            Volume: &csi.Volume{
+                // Ugly, but VolumeContext isn't passed to DeleteVolume :-(
+                VolumeId: string(volumeIdJson),
+                CapacityBytes: volSize,
+            },
+        }, nil
+    }
+
+    args := []string{ "create", volName, "-s", fmt.Sprintf("%v", volSize), "--pool", pool }
 
     // Support creation from snapshot
     var src *csi.VolumeContentSource
@@ -261,6 +273,12 @@ func (cs *ControllerServer) DeleteVolume(ctx context.Context, req *csi.DeleteVol
         return nil, err
     }
 
+    if (ctxVars["vitastorfs"] != "")
+    {
+        // FIXME: Delete FS subdirectory
+        return &csi.DeleteVolumeResponse{}, nil
+    }
+
     _, err = invokeCLI(ctxVars, []string{ "rm", volName })
     if (err != nil)
     {
@@ -295,19 +313,72 @@ func (cs *ControllerServer) ValidateVolumeCapabilities(ctx context.Context, req
     {
         return nil, status.Error(codes.InvalidArgument, "volumeId is nil")
     }
+    volVars := make(map[string]string)
+    err := json.Unmarshal([]byte(volumeID), &volVars)
+    if (err != nil)
+    {
+        return nil, status.Error(codes.Internal, "volume ID not in JSON format")
+    }
+    ctxVars, err := GetConnectionParams(volVars)
+    if (err != nil)
+    {
+        return nil, err
+    }
+
     volumeCapabilities := req.GetVolumeCapabilities()
     if (volumeCapabilities == nil)
     {
         return nil, status.Error(codes.InvalidArgument, "volumeCapabilities is nil")
     }
 
+    err = cs.checkCaps(volumeCapabilities, ctxVars["vitastorfs"] != "")
+    if (err != nil)
+    {
+        return nil, err
+    }
+
+    return &csi.ValidateVolumeCapabilitiesResponse{
+        Confirmed: &csi.ValidateVolumeCapabilitiesResponse_Confirmed{
+            VolumeCapabilities: req.VolumeCapabilities,
+        },
+    }, nil
+}
+
+func (cs *ControllerServer) checkCaps(volumeCapabilities []*csi.VolumeCapability, fs bool) error
+{
     var volumeCapabilityAccessModes []*csi.VolumeCapability_AccessMode
     for _, mode := range []csi.VolumeCapability_AccessMode_Mode{
         csi.VolumeCapability_AccessMode_SINGLE_NODE_WRITER,
-        csi.VolumeCapability_AccessMode_MULTI_NODE_MULTI_WRITER,
+        csi.VolumeCapability_AccessMode_SINGLE_NODE_READER_ONLY,
+        csi.VolumeCapability_AccessMode_MULTI_NODE_READER_ONLY,
+        csi.VolumeCapability_AccessMode_SINGLE_NODE_SINGLE_WRITER,
+        csi.VolumeCapability_AccessMode_SINGLE_NODE_MULTI_WRITER,
     } {
         volumeCapabilityAccessModes = append(volumeCapabilityAccessModes, &csi.VolumeCapability_AccessMode{Mode: mode})
     }
+    for _, capability := range volumeCapabilities
+    {
+        if (capability.GetBlock() != nil)
+        {
+            if (fs)
+            {
+                return status.Errorf(codes.InvalidArgument, "%v not supported with FS-based volumes", capability)
+            }
+            for _, mode := range []csi.VolumeCapability_AccessMode_Mode{
+                csi.VolumeCapability_AccessMode_MULTI_NODE_SINGLE_WRITER,
+                csi.VolumeCapability_AccessMode_MULTI_NODE_MULTI_WRITER,
+            } {
+                volumeCapabilityAccessModes = append(volumeCapabilityAccessModes, &csi.VolumeCapability_AccessMode{Mode: mode})
+            }
+            break
+        }
+    }
+
+    if (fs)
+    {
+        // All access modes including RWX are supported with FS-based volumes
+        return nil
+    }
 
     capabilitySupport := false
     for _, capability := range volumeCapabilities
@@ -323,14 +394,10 @@ func (cs *ControllerServer) ValidateVolumeCapabilities(ctx context.Context, req
 
     if (!capabilitySupport)
     {
-        return nil, status.Errorf(codes.NotFound, "%v not supported", req.GetVolumeCapabilities())
+        return status.Errorf(codes.InvalidArgument, "%v not supported", volumeCapabilities)
     }
 
-    return &csi.ValidateVolumeCapabilitiesResponse{
-        Confirmed: &csi.ValidateVolumeCapabilitiesResponse_Confirmed{
-            VolumeCapabilities: req.VolumeCapabilities,
-        },
-    }, nil
+    return nil
 }
 
 // ListVolumes returns a list of volumes
@@ -419,6 +486,12 @@ func (cs *ControllerServer) CreateSnapshot(ctx context.Context, req *csi.CreateS
     {
         return nil, status.Error(codes.Internal, "volume ID not in JSON format")
     }
+
+    if (ctxVars["vitastorfs"] != "")
+    {
+        return nil, status.Error(codes.InvalidArgument, "VitastorFS doesn't support snapshots")
+    }
+
     volName := ctxVars["name"]
 
     // Create image using vitastor-cli
@@ -477,6 +550,11 @@ func (cs *ControllerServer) DeleteSnapshot(ctx context.Context, req *csi.DeleteS
         return nil, err
     }
 
+    if (ctxVars["vitastorfs"] != "")
+    {
+        return nil, status.Error(codes.InvalidArgument, "VitastorFS doesn't support snapshots")
+    }
+
     _, err = invokeCLI(ctxVars, []string{ "rm", volName+"@"+snapName })
     if (err != nil)
     {
@@ -508,6 +586,11 @@ func (cs *ControllerServer) ListSnapshots(ctx context.Context, req *csi.ListSnap
         return nil, err
     }
 
+    if (ctxVars["vitastorfs"] != "")
+    {
+        return nil, status.Error(codes.InvalidArgument, "VitastorFS doesn't support snapshots")
+    }
+
     inodeCfg, err := invokeList(ctxVars, volName+"@*", false)
     if (err != nil)
     {
@@ -571,6 +654,16 @@ func (cs *ControllerServer) ControllerExpandVolume(ctx context.Context, req *csi
         return nil, err
     }
 
+    if (ctxVars["vitastorfs"] != "")
+    {
+        // Nothing to change
+        // FIXME: Support quotas and change quota here
+        return &csi.ControllerExpandVolumeResponse{
+            CapacityBytes: req.CapacityRange.RequiredBytes,
+            NodeExpansionRequired: false,
+        }, nil
+    }
+
     inodeCfg, err := invokeList(ctxVars, volName, true)
     if (err != nil)
     {

csi/src/nodeserver.go

@@ -5,11 +5,15 @@ package vitastor
 
 import (
     "context"
+    "crypto/sha1"
+    "encoding/hex"
     "encoding/json"
     "fmt"
     "os"
     "os/exec"
     "path/filepath"
+    "regexp"
+    "strconv"
     "strings"
     "sync"
     "syscall"
@@ -29,13 +33,14 @@ import (
 type NodeServer struct
 {
     *Driver
-    useVduse bool
-    stateDir string
-    mounter mount.Interface
+    useVduse        bool
+    stateDir        string
+    nfsStageDir     string
+    mounter         mount.Interface
     restartInterval time.Duration
-    mu sync.Mutex
-    cond *sync.Cond
-    volumeLocks map[string]bool
+    mu              sync.Mutex
+    cond            *sync.Cond
+    volumeLocks     map[string]bool
 }
 
 type DeviceState struct
@@ -48,6 +53,15 @@ type DeviceState struct
     PidFile    string `json:"pidFile"`
 }
 
+type NfsState struct
+{
+    ConfigPath string `json:"configPath"`
+    FsName     string `json:"fsName"`
+    Pool       string `json:"pool"`
+    Path       string `json:"path"`
+    Port       int    `json:"port"`
+}
+
 // NewNodeServer create new instance node
 func NewNodeServer(driver *Driver) *NodeServer
 {
@@ -60,11 +74,17 @@ func NewNodeServer(driver *Driver) *NodeServer
     {
         stateDir += "/"
     }
+    nfsStageDir := os.Getenv("NFS_STAGE_DIR")
+    if (nfsStageDir == "")
+    {
+        nfsStageDir = "/var/lib/kubelet/plugins/csi.vitastor.io/nfs"
+    }
     ns := &NodeServer{
-        Driver: driver,
-        useVduse: checkVduseSupport(),
-        stateDir: stateDir,
-        mounter: mount.New(""),
+        Driver:      driver,
+        useVduse:    checkVduseSupport(),
+        stateDir:    stateDir,
+        nfsStageDir: nfsStageDir,
+        mounter:     mount.New(""),
         volumeLocks: make(map[string]bool),
     }
     ns.cond = sync.NewCond(&ns.mu)
@@ -123,12 +143,12 @@ func (ns *NodeServer) restarter()
 func (ns *NodeServer) restoreVduseDaemons()
 {
     pattern := ns.stateDir+"vitastor-vduse-*.json"
-    matches, err := filepath.Glob(pattern)
+    stateFiles, err := filepath.Glob(pattern)
     if (err != nil)
     {
         klog.Errorf("failed to list %s: %v", pattern, err)
     }
-    if (len(matches) == 0)
+    if (len(stateFiles) == 0)
     {
         return
     }
@@ -146,59 +166,162 @@ func (ns *NodeServer) restoreVduseDaemons()
         klog.Errorf("/sbin/vdpa -j dev list returned bad JSON (error %v): %v", err, string(devListJSON))
         return
     }
-    for _, stateFile := range matches
+    for _, stateFile := range stateFiles
     {
-        vdpaId := filepath.Base(stateFile)
-        vdpaId = vdpaId[0:len(vdpaId)-5]
-        // Check if VDPA device is still added to the bus
-        if (devs[vdpaId] == nil)
-        {
-            // Unused, clean it up
-            unmapVduseById(ns.stateDir, vdpaId)
-            continue
-        }
+        ns.checkVduseState(stateFile, devs)
+    }
+}
 
-        stateJSON, err := os.ReadFile(stateFile)
+func (ns *NodeServer) checkVduseState(stateFile string, devs map[string]interface{})
+{
+    // Check if VDPA device is still added to the bus
+    vdpaId := filepath.Base(stateFile)
+    vdpaId = vdpaId[0:len(vdpaId)-5]
+    if (devs[vdpaId] == nil)
+    {
+        // Unused, clean it up
+        unmapVduseById(ns.stateDir, vdpaId)
+        return
+    }
+
+    // Read state file
+    stateJSON, err := os.ReadFile(stateFile)
+    if (err != nil)
+    {
+        klog.Warningf("error reading state file %v: %v", stateFile, err)
+        return
+    }
+    var state DeviceState
+    err = json.Unmarshal(stateJSON, &state)
+    if (err != nil)
+    {
+        klog.Warningf("state file %v contains invalid JSON (error %v): %v", stateFile, err, string(stateJSON))
+        return
+    }
+
+    // Lock volume
+    ns.lockVolume(state.ConfigPath+":block:"+state.Image)
+    defer ns.unlockVolume(state.ConfigPath+":block:"+state.Image)
+
+    // Recheck state file after locking
+    _, err = os.ReadFile(stateFile)
+    if (err != nil)
+    {
+        klog.Warningf("state file %v disappeared, skipping volume", stateFile)
+        return
+    }
+
+    // Check if the storage daemon is still active
+    pidFile := ns.stateDir + vdpaId + ".pid"
+    exists := false
+    proc, err := findByPidFile(pidFile)
+    if (err == nil)
+    {
+        exists = proc.Signal(syscall.Signal(0)) == nil
+    }
+    if (!exists)
+    {
+        // Restart daemon
+        klog.Warningf("restarting storage daemon for volume %v (VDPA ID %v)", state.Image, vdpaId)
+        err = startStorageDaemon(vdpaId, state.Image, pidFile, state.ConfigPath, state.Readonly)
         if (err != nil)
         {
-            klog.Warningf("error reading state file %v: %v", stateFile, err)
-            continue
+            klog.Warningf("failed to restart storage daemon for volume %v: %v", state.Image, err)
         }
-        var state DeviceState
-        err = json.Unmarshal(stateJSON, &state)
+    }
+}
+
+func (ns *NodeServer) restoreNfsDaemons()
+{
+    pattern := ns.stateDir+"vitastor-nfs-*.json"
+    stateFiles, err := filepath.Glob(pattern)
+    if (err != nil)
+    {
+        klog.Errorf("failed to list %s: %v", pattern, err)
+    }
+    if (len(stateFiles) == 0)
+    {
+        return
+    }
+    activeNFS, err := ns.listActiveNFS()
+    if (err != nil)
+    {
+        return
+    }
+    // Check all state files and try to restore active mounts
+    for _, stateFile := range stateFiles
+    {
+        ns.checkNfsState(stateFile, activeNFS)
+    }
+}
+
+func (ns *NodeServer) readNfsState(stateFile string, allowNotExists bool) (*NfsState, error)
+{
+    stateJSON, err := os.ReadFile(stateFile)
+    if (err != nil)
+    {
+        if (allowNotExists && os.IsNotExist(err))
+        {
+            return nil, nil
+        }
+        klog.Warningf("error reading state file %v: %v", stateFile, err)
+        return nil, err
+    }
+    var state NfsState
+    err = json.Unmarshal(stateJSON, &state)
+    if (err != nil)
+    {
+        klog.Warningf("state file %v contains invalid JSON (error %v): %v", stateFile, err, string(stateJSON))
+        return nil, err
+    }
+    return &state, nil
+}
+
+func (ns *NodeServer) checkNfsState(stateFile string, activeNfs map[int][]string)
+{
+    // Read state file
+    state, err := ns.readNfsState(stateFile, false)
+    if (err != nil)
+    {
+        return
+    }
+    // Lock FS
+    ns.lockVolume(state.ConfigPath+":fs:"+state.FsName)
+    defer ns.unlockVolume(state.ConfigPath+":fs:"+state.FsName)
+    // Check if NFS at this port is still mounted
+    pidFile := ns.stateDir + filepath.Base(stateFile)
+    pidFile = pidFile[0:len(pidFile)-5] + ".pid"
+    if (len(activeNfs[state.Port]) == 0)
+    {
+        // this is a stale state file, remove it
+        klog.Warningf("state file %v contains stale mount at port %d, removing it", stateFile, state.Port)
+        ns.stopNFS(stateFile, pidFile)
+        return
+    }
+    // Check PID file
+    exists := false
+    proc, err := findByPidFile(pidFile)
+    if (err == nil)
+    {
+        exists = proc.Signal(syscall.Signal(0)) == nil
+    }
+    if (!exists)
+    {
+        // Restart vitastor-nfs server
+        klog.Warningf("restarting NFS server for FS %v at port %v", state.FsName, state.Port)
+        _, _, err := system(
+            "/usr/bin/vitastor-nfs", "start",
+            "--pidfile", pidFile,
+            "--bind", "127.0.0.1",
+            "--port", fmt.Sprintf("%d", state.Port),
+            "--fs", state.FsName,
+            "--pool", state.Pool,
+            "--portmap", "0",
+        )
         if (err != nil)
         {
-            klog.Warningf("state file %v contains invalid JSON (error %v): %v", stateFile, err, string(stateJSON))
-            continue
+            klog.Warningf("failed to restart NFS server for FS %v: %v", state.FsName, err)
         }
-
-        ns.lockVolume(state.ConfigPath+":"+state.Image)
-
-        // Recheck state file after locking
-        _, err = os.ReadFile(stateFile)
-        if (err != nil)
-        {
-            klog.Warningf("state file %v disappeared, skipping volume", stateFile)
-            ns.unlockVolume(state.ConfigPath+":"+state.Image)
-            continue
-        }
-
-        // Check if the storage daemon is still active
-        pidFile := ns.stateDir + vdpaId + ".pid"
-        exists := false
-        proc, err := findByPidFile(pidFile)
-        if (err == nil)
-        {
-            exists = proc.Signal(syscall.Signal(0)) == nil
-        }
-        if (!exists)
-        {
-            // Restart daemon
-            klog.Warningf("restarting storage daemon for volume %v (VDPA ID %v)", state.Image, vdpaId)
-            _ = startStorageDaemon(vdpaId, state.Image, pidFile, state.ConfigPath, state.Readonly)
-        }
-
-        ns.unlockVolume(state.ConfigPath+":"+state.Image)
     }
 }
 
@@ -220,14 +343,44 @@ func (ns *NodeServer) NodeStageVolume(ctx context.Context, req *csi.NodeStageVol
     }
     volName := ctxVars["name"]
 
-    ns.lockVolume(ctxVars["configPath"]+":"+volName)
-    defer ns.unlockVolume(ctxVars["configPath"]+":"+volName)
+    if (ctxVars["vitastorfs"] != "")
+    {
+        return &csi.NodeStageVolumeResponse{}, nil
+    }
+
+    ns.lockVolume(ctxVars["configPath"]+":block:"+volName)
+    defer ns.unlockVolume(ctxVars["configPath"]+":block:"+volName)
 
     targetPath := req.GetStagingTargetPath()
     isBlock := req.GetVolumeCapability().GetBlock() != nil
 
     // Check that it's not already mounted
-    _, err = mount.IsNotMountPoint(ns.mounter, targetPath)
+    notmnt, err := mount.IsNotMountPoint(ns.mounter, targetPath)
+    if (err == nil)
+    {
+        if (!notmnt)
+        {
+            klog.Errorf("target path %s is already mounted", targetPath)
+            return nil, fmt.Errorf("target path %s is already mounted", targetPath)
+        }
+        var finfo os.FileInfo
+        finfo, err = os.Stat(targetPath)
+        if (err != nil)
+        {
+            klog.Errorf("failed to stat %s: %v", targetPath, err)
+            return nil, err
+        }
+        if (finfo.IsDir() != (!isBlock))
+        {
+            err = os.Remove(targetPath)
+            if (err != nil)
+            {
+                klog.Errorf("failed to remove %s (to recreate it with correct type): %v", targetPath, err)
+                return nil, err
+            }
+            err = os.ErrNotExist
+        }
+    }
     if (err != nil)
     {
         if (os.IsNotExist(err))
@@ -280,6 +433,7 @@ func (ns *NodeServer) NodeStageVolume(ctx context.Context, req *csi.NodeStageVol
     diskMounter := &mount.SafeFormatAndMount{Interface: ns.mounter, Exec: utilexec.New()}
     if (isBlock)
     {
+        klog.Infof("bind-mounting %s to %s", devicePath, targetPath)
         err = diskMounter.Mount(devicePath, targetPath, "", []string{"bind"})
     }
     else
@@ -309,39 +463,40 @@ func (ns *NodeServer) NodeStageVolume(ctx context.Context, req *csi.NodeStageVol
         readOnly := Contains(opt, "ro")
         if (existingFormat == "" && !readOnly)
         {
-            var cmdOut []byte
             switch fsType
             {
                 case "ext4":
                     args := []string{"-m0", "-Enodiscard,lazy_itable_init=1,lazy_journal_init=1", devicePath}
-                    cmdOut, err = diskMounter.Exec.Command("mkfs.ext4", args...).CombinedOutput()
+                    _, err = systemCombined("mkfs.ext4", args...)
                 case "xfs":
-                    cmdOut, err = diskMounter.Exec.Command("mkfs.xfs", "-K", devicePath).CombinedOutput()
+                    _, err = systemCombined("mkfs.xfs", "-K", devicePath)
             }
             if (err != nil)
             {
-                klog.Errorf("failed to run mkfs error: %v, output: %v", err, string(cmdOut))
                 goto unmap
             }
         }
 
+        klog.Infof("formatting and mounting %s to %s with FS %s, options: %v", devicePath, targetPath, fsType, opt)
         err = diskMounter.FormatAndMount(devicePath, targetPath, fsType, opt)
+        if (err == nil)
+        {
+            klog.Infof("successfully mounted %s to %s", devicePath, targetPath)
+        }
 
         // Try to run online resize on mount.
         // FIXME: Implement online resize. It requires online resize support in vitastor-nbd.
         if (err == nil && existingFormat != "" && !readOnly)
         {
-            var cmdOut []byte
             switch (fsType)
             {
                 case "ext4":
-                    cmdOut, err = diskMounter.Exec.Command("resize2fs", devicePath).CombinedOutput()
+                    _, err = systemCombined("resize2fs", devicePath)
                 case "xfs":
-                    cmdOut, err = diskMounter.Exec.Command("xfs_growfs", devicePath).CombinedOutput()
+                    _, err = systemCombined("xfs_growfs", devicePath)
             }
             if (err != nil)
             {
-                klog.Errorf("failed to run resizefs error: %v, output: %v", err, string(cmdOut))
                 goto unmap
             }
         }
@@ -381,11 +536,16 @@ func (ns *NodeServer) NodeUnstageVolume(ctx context.Context, req *csi.NodeUnstag
     }
     volName := ctxVars["name"]
 
-    ns.lockVolume(ctxVars["configPath"]+":"+volName)
-    defer ns.unlockVolume(ctxVars["configPath"]+":"+volName)
+    if (ctxVars["vitastorfs"] != "")
+    {
+        return &csi.NodeUnstageVolumeResponse{}, nil
+    }
+
+    ns.lockVolume(ctxVars["configPath"]+":block:"+volName)
+    defer ns.unlockVolume(ctxVars["configPath"]+":block:"+volName)
 
     targetPath := req.GetStagingTargetPath()
-    devicePath, refCount, err := mount.GetDeviceNameFromMount(ns.mounter, targetPath)
+    devicePath, _, err := mount.GetDeviceNameFromMount(ns.mounter, targetPath)
     if (err != nil)
     {
         if (os.IsNotExist(err))
@@ -402,6 +562,16 @@ func (ns *NodeServer) NodeUnstageVolume(ctx context.Context, req *csi.NodeUnstag
         return &csi.NodeUnstageVolumeResponse{}, nil
     }
 
+    refList, err := ns.mounter.GetMountRefs(targetPath)
+    if (err != nil)
+    {
+        return nil, err
+    }
+    if (len(refList) > 0)
+    {
+        klog.Warningf("%s is still referenced: %v", targetPath, refList)
+    }
+
     // unmount
     err = mount.CleanupMountPoint(targetPath, ns.mounter, false)
     if (err != nil)
@@ -410,7 +580,7 @@ func (ns *NodeServer) NodeUnstageVolume(ctx context.Context, req *csi.NodeUnstag
     }
 
     // unmap device
-    if (refCount == 1)
+    if (len(refList) == 0)
     {
         if (!ns.useVduse)
         {
@@ -425,6 +595,153 @@ func (ns *NodeServer) NodeUnstageVolume(ctx context.Context, req *csi.NodeUnstag
     return &csi.NodeUnstageVolumeResponse{}, nil
 }
 
+// Mount or check if NFS is already mounted
+func (ns *NodeServer) mountNFS(ctxVars map[string]string) (string, error)
+{
+    sum := sha1.Sum([]byte(ctxVars["configPath"]+":fs:"+ctxVars["vitastorfs"]))
+    nfsHash := hex.EncodeToString(sum[:])
+    stateFile := ns.stateDir+"vitastor-nfs-"+nfsHash+".json"
+    pidFile := ns.stateDir+"vitastor-nfs-"+nfsHash+".pid"
+    mountPath := ns.nfsStageDir+"/"+nfsHash
+    state, err := ns.readNfsState(stateFile, true)
+    if (state != nil)
+    {
+        return state.Path, nil
+    }
+    if (err != nil)
+    {
+        return "", err
+    }
+    err = os.MkdirAll(mountPath, 0777)
+    if (err != nil)
+    {
+        return "", err
+    }
+    // Create a new mount
+    state = &NfsState{
+        ConfigPath: ctxVars["configPath"],
+        FsName:     ctxVars["vitastorfs"],
+        Pool:       ctxVars["pool"],
+        Path:       mountPath,
+    }
+    klog.Infof("starting new NFS server for FS %v", state.FsName)
+    stdout, _, err := system(
+        "/usr/bin/vitastor-nfs", "start",
+        "--pidfile", pidFile,
+        "--bind", "127.0.0.1",
+        "--port", "auto",
+        "--fs", state.FsName,
+        "--pool", state.Pool,
+        "--portmap", "0",
+    )
+    if (err != nil)
+    {
+        return "", err
+    }
+    match := regexp.MustCompile("Port: (\\d+)").FindStringSubmatch(string(stdout))
+    if (match == nil)
+    {
+        klog.Errorf("failed to find port in vitastor-nfs output: %v", string(stdout))
+        ns.stopNFS(stateFile, pidFile)
+        return "", fmt.Errorf("failed to find port in vitastor-nfs output (bad vitastor-nfs version?)")
+    }
+    port, _ := strconv.ParseUint(match[1], 0, 16)
+    state.Port = int(port)
+    // Write state file
+    stateJSON, _ := json.Marshal(state)
+    err = os.WriteFile(stateFile, stateJSON, 0600)
+    if (err != nil)
+    {
+        klog.Errorf("failed to write state file %v", stateFile)
+        ns.stopNFS(stateFile, pidFile)
+        return "", err
+    }
+    // Mount NFS
+    _, _, err = system(
+        "mount", "-t", "nfs", "127.0.0.1:/", state.Path,
+        "-o", fmt.Sprintf("port=%d,mountport=%d,nfsvers=3,soft,nolock,tcp", port, port),
+    )
+    if (err != nil)
+    {
+        ns.stopNFS(stateFile, pidFile)
+        return "", err
+    }
+    return state.Path, nil
+}
+
+// Mount or check if NFS is already mounted
+func (ns *NodeServer) checkStopNFS(ctxVars map[string]string)
+{
+    sum := sha1.Sum([]byte(ctxVars["configPath"]+":fs:"+ctxVars["vitastorfs"]))
+    nfsHash := hex.EncodeToString(sum[:])
+    stateFile := ns.stateDir+"vitastor-nfs-"+nfsHash+".json"
+    pidFile := ns.stateDir+"vitastor-nfs-"+nfsHash+".pid"
+    mountPath := ns.nfsStageDir+"/"+nfsHash
+    state, err := ns.readNfsState(stateFile, true)
+    if (state == nil)
+    {
+        return
+    }
+    activeNFS, err := ns.listActiveNFS()
+    if (err != nil)
+    {
+        return
+    }
+    if (len(activeNFS[state.Port]) > 0)
+    {
+        return
+    }
+    // All volume mounts are detached, unmount the root mount and kill the server
+    err = mount.CleanupMountPoint(mountPath, ns.mounter, false)
+    if (err != nil)
+    {
+        klog.Errorf("failed to unmount %v: %v", mountPath, err)
+        return
+    }
+    ns.stopNFS(stateFile, pidFile)
+}
+
+func (ns *NodeServer) stopNFS(stateFile, pidFile string)
+{
+    err := killByPidFile(pidFile)
+    if (err != nil)
+    {
+        klog.Errorf("failed to kill process with pid from %v: %v", pidFile, err)
+    }
+    os.Remove(pidFile)
+    os.Remove(stateFile)
+}
+
+func (ns *NodeServer) listActiveNFS() (map[int][]string, error)
+{
+    mounts, err := mount.ParseMountInfo("/proc/self/mountinfo")
+    if (err != nil)
+    {
+        klog.Errorf("failed to list mounts: %v", err)
+        return nil, err
+    }
+    activeNFS := make(map[int][]string)
+    for _, mount := range mounts
+    {
+        // Volume mounts always refer to subpaths
+        if (mount.FsType == "nfs" && mount.Root != "/")
+        {
+            for _, opt := range mount.MountOptions
+            {
+                if (strings.HasPrefix(opt, "port="))
+                {
+                    port64, err := strconv.ParseUint(opt[5:], 10, 16)
+                    if (err == nil)
+                    {
+                        activeNFS[int(port64)] = append(activeNFS[int(port64)], mount.MountPoint)
+                    }
+                }
+            }
+        }
+    }
+    return activeNFS, nil
+}
+
 // NodePublishVolume mounts the volume mounted to the staging path to the target path
 func (ns *NodeServer) NodePublishVolume(ctx context.Context, req *csi.NodePublishVolumeRequest) (*csi.NodePublishVolumeResponse, error)
 {
@@ -443,23 +760,39 @@ func (ns *NodeServer) NodePublishVolume(ctx context.Context, req *csi.NodePublis
     }
     volName := ctxVars["name"]
 
-    ns.lockVolume(ctxVars["configPath"]+":"+volName)
-    defer ns.unlockVolume(ctxVars["configPath"]+":"+volName)
+    if (ctxVars["vitastorfs"] != "")
+    {
+        ns.lockVolume(ctxVars["configPath"]+":fs:"+ctxVars["vitastorfs"])
+        defer ns.unlockVolume(ctxVars["configPath"]+":fs:"+ctxVars["vitastorfs"])
+    }
+    else
+    {
+        ns.lockVolume(ctxVars["configPath"]+":block:"+volName)
+        defer ns.unlockVolume(ctxVars["configPath"]+":block:"+volName)
+    }
 
     stagingTargetPath := req.GetStagingTargetPath()
     targetPath := req.GetTargetPath()
     isBlock := req.GetVolumeCapability().GetBlock() != nil
 
-    // Check that stagingTargetPath is mounted
-    _, err = mount.IsNotMountPoint(ns.mounter, stagingTargetPath)
-    if (err != nil)
+    if (ctxVars["vitastorfs"] == "")
     {
-        klog.Errorf("staging path %v is not mounted: %v", stagingTargetPath, err)
-        return nil, fmt.Errorf("staging path %v is not mounted: %v", stagingTargetPath, err)
+        // Check that stagingTargetPath is mounted
+        notmnt, err := mount.IsNotMountPoint(ns.mounter, stagingTargetPath)
+        if (err != nil)
+        {
+            klog.Errorf("staging path %v is not mounted: %w", stagingTargetPath, err)
+            return nil, fmt.Errorf("staging path %v is not mounted: %w", stagingTargetPath, err)
+        }
+        else if (notmnt)
+        {
+            klog.Errorf("staging path %v is not mounted", stagingTargetPath)
+            return nil, fmt.Errorf("staging path %v is not mounted", stagingTargetPath)
+        }
     }
 
     // Check that targetPath is not already mounted
-    _, err = mount.IsNotMountPoint(ns.mounter, targetPath)
+    notmnt, err := mount.IsNotMountPoint(ns.mounter, targetPath)
     if (err != nil)
     {
         if (os.IsNotExist(err))
@@ -494,6 +827,29 @@ func (ns *NodeServer) NodePublishVolume(ctx context.Context, req *csi.NodePublis
             return nil, err
         }
     }
+    else if (!notmnt)
+    {
+        klog.Errorf("target path %s is already mounted", targetPath)
+        return nil, fmt.Errorf("target path %s is already mounted", targetPath)
+    }
+
+    if (ctxVars["vitastorfs"] != "")
+    {
+        nfspath, err := ns.mountNFS(ctxVars)
+        if (err != nil)
+        {
+            ns.checkStopNFS(ctxVars)
+            return nil, err
+        }
+        // volName should include prefix
+        stagingTargetPath = nfspath+"/"+volName
+        err = os.MkdirAll(stagingTargetPath, 0777)
+        if (err != nil && !os.IsExist(err))
+        {
+            ns.checkStopNFS(ctxVars)
+            return nil, err
+        }
+    }
 
     execArgs := []string{"--bind", stagingTargetPath, targetPath}
     if (req.GetReadonly())
@@ -506,6 +862,10 @@ func (ns *NodeServer) NodePublishVolume(ctx context.Context, req *csi.NodePublis
     out, err := cmd.Output()
     if (err != nil)
     {
+        if (ctxVars["vitastorfs"] != "")
+        {
+            ns.checkStopNFS(ctxVars)
+        }
         return nil, fmt.Errorf("Error running mount %v: %s", strings.Join(execArgs, " "), out)
     }
 
@@ -525,8 +885,16 @@ func (ns *NodeServer) NodeUnpublishVolume(ctx context.Context, req *csi.NodeUnpu
     }
     volName := ctxVars["name"]
 
-    ns.lockVolume(ctxVars["configPath"]+":"+volName)
-    defer ns.unlockVolume(ctxVars["configPath"]+":"+volName)
+    if (ctxVars["vitastorfs"] != "")
+    {
+        ns.lockVolume(ctxVars["configPath"]+":fs:"+ctxVars["vitastorfs"])
+        defer ns.unlockVolume(ctxVars["configPath"]+":fs:"+ctxVars["vitastorfs"])
+    }
+    else
+    {
+        ns.lockVolume(ctxVars["configPath"]+":block:"+volName)
+        defer ns.unlockVolume(ctxVars["configPath"]+":block:"+volName)
+    }
 
     targetPath := req.GetTargetPath()
     devicePath, _, err := mount.GetDeviceNameFromMount(ns.mounter, targetPath)
@@ -553,6 +921,11 @@ func (ns *NodeServer) NodeUnpublishVolume(ctx context.Context, req *csi.NodeUnpu
         return nil, err
     }
 
+    if (ctxVars["vitastorfs"] != "")
+    {
+        ns.checkStopNFS(ctxVars)
+    }
+
     return &csi.NodeUnpublishVolumeResponse{}, nil
 }
 

csi/src/utils.go

@@ -4,6 +4,7 @@
 package vitastor
 
 import (
+    "bytes"
     "errors"
     "encoding/json"
     "fmt"
@@ -15,6 +16,8 @@ import (
     "syscall"
 
     "k8s.io/klog"
+    "google.golang.org/grpc/codes"
+    "google.golang.org/grpc/status"
 )
 
 func Contains(list []string, s string) bool
@@ -73,6 +76,10 @@ func checkVduseSupport() bool
             " For VDUSE you need at least Linux 5.15 and the following kernel modules: vdpa, virtio-vdpa, vduse.",
         )
     }
+    else
+    {
+        klog.Infof("VDUSE support enabled successfully")
+    }
     return vduse
 }
 
@@ -97,6 +104,7 @@ func mapNbd(volName string, ctxVars map[string]string, readonly bool) (string, e
     {
         return "", fmt.Errorf("vitastor-nbd did not return the name of NBD device. output: %s", stderr)
     }
+    klog.Infof("Attached volume %s via NBD as %s", volName, dev)
     return dev, err
 }
 
@@ -217,6 +225,7 @@ func mapVduse(stateDir string, volName string, ctxVars map[string]string, readon
                     err = os.WriteFile(stateFile, stateJSON, 0600)
                     if (err == nil)
                     {
+                        klog.Infof("Attached volume %s via VDUSE as %s (VDPA ID %s)", volName, blockdev, vdpaId)
                         return blockdev, vdpaId, nil
                     }
                 }
@@ -299,3 +308,35 @@ func unmapVduseById(stateDir, vdpaId string)
         os.Remove(pidFile)
     }
 }
+
+func system(program string, args ...string) ([]byte, []byte, error)
+{
+    klog.Infof("Running "+program+" "+strings.Join(args, " "))
+    c := exec.Command(program, args...)
+    var stdout, stderr bytes.Buffer
+    c.Stdout, c.Stderr = &stdout, &stderr
+    err := c.Run()
+    if (err != nil)
+    {
+        stdoutStr, stderrStr := string(stdout.Bytes()), string(stderr.Bytes())
+        klog.Errorf(program+" "+strings.Join(args, " ")+" failed: %s\nOutput:\n%s", err, stdoutStr+stderrStr)
+        return nil, nil, status.Error(codes.Internal, stdoutStr+stderrStr+" (status "+err.Error()+")")
+    }
+    return stdout.Bytes(), stderr.Bytes(), nil
+}
+
+func systemCombined(program string, args ...string) ([]byte, error)
+{
+    klog.Infof("Running "+program+" "+strings.Join(args, " "))
+    c := exec.Command(program, args...)
+    var out bytes.Buffer
+    c.Stdout, c.Stderr = &out, &out
+    err := c.Run()
+    if (err != nil)
+    {
+        outStr := string(out.Bytes())
+        klog.Errorf(program+" "+strings.Join(args, " ")+" failed: %s, status %s\n", outStr, err)
+        return nil, status.Error(codes.Internal, outStr+" (status "+err.Error()+")")
+    }
+    return out.Bytes(), nil
+}

debian/changelog

@@ -1,4 +1,4 @@
-vitastor (1.7.1-1) unstable; urgency=medium
+vitastor (2.0.0-1) unstable; urgency=medium
 
   * Bugfixes
 

debian/control

@@ -2,7 +2,10 @@ Source: vitastor
 Section: admin
 Priority: optional
 Maintainer: Vitaliy Filippov <vitalif@yourcmc.ru>
-Build-Depends: debhelper, liburing-dev (>= 0.6), g++ (>= 8), libstdc++6 (>= 8), linux-libc-dev, libgoogle-perftools-dev, libjerasure-dev, libgf-complete-dev, libibverbs-dev, libisal-dev, cmake, pkg-config, libnl-3-dev, libnl-genl-3-dev
+Build-Depends: debhelper, liburing-dev (>= 0.6), g++ (>= 8), libstdc++6 (>= 8),
+  linux-libc-dev, libgoogle-perftools-dev, libjerasure-dev, libgf-complete-dev,
+  libibverbs-dev, libisal-dev, cmake, pkg-config, libnl-3-dev, libnl-genl-3-dev,
+  node-bindings <!nocheck>, node-gyp, node-nan
 Standards-Version: 4.5.0
 Homepage: https://vitastor.io/
 Rules-Requires-Root: no
@@ -53,3 +56,15 @@ Architecture: amd64
 Depends: ${shlibs:Depends}, ${misc:Depends}, vitastor-client (= ${binary:Version})
 Description: Vitastor Proxmox Virtual Environment storage plugin
  Vitastor storage plugin for Proxmox Virtual Environment.
+
+Package: vitastor-opennebula
+Architecture: amd64
+Depends: ${shlibs:Depends}, ${misc:Depends}, vitastor-client, patch, python3, jq
+Description: Vitastor OpenNebula storage plugin
+ Vitastor storage plugin for OpenNebula.
+
+Package: node-vitastor
+Architecture: amd64
+Depends: ${shlibs:Depends}, ${misc:Depends}, node-bindings
+Description: Node.js bindings for Vitastor client
+ Node.js native bindings for the Vitastor client library (vitastor-client).

debian/node-vitastor.install

@@ -0,0 +1 @@
+usr/lib/x86_64-linux-gnu/nodejs/vitastor

debian/patched-qemu.Dockerfile

@@ -1,17 +1,23 @@
 # Build patched QEMU for Debian inside a container
 # cd ..; podman build --build-arg REL=bullseye -v `pwd`/packages:/root/packages -f debian/patched-qemu.Dockerfile .
 
+ARG DISTRO=debian
 ARG REL=
-FROM debian:$REL
+FROM $DISTRO:$REL
+ARG DISTRO=debian
 ARG REL=
 
 WORKDIR /root
 
 RUN if [ "$REL" = "buster" -o "$REL" = "bullseye" -o "$REL" = "bookworm" ]; then \
-        echo "deb http://deb.debian.org/debian $REL-backports main" >> /etc/apt/sources.list; \
+        if [ "$REL" = "buster" ]; then \
+            echo "deb http://archive.debian.org/debian $REL-backports main" >> /etc/apt/sources.list; \
+        else \
+            echo "deb http://deb.debian.org/debian $REL-backports main" >> /etc/apt/sources.list; \
+        fi; \
         echo >> /etc/apt/preferences; \
         echo 'Package: *' >> /etc/apt/preferences; \
-        echo "Pin: release a=$REL-backports" >> /etc/apt/preferences; \
+        echo "Pin: release n=$REL-backports" >> /etc/apt/preferences; \
         echo 'Pin-Priority: 500' >> /etc/apt/preferences; \
     fi; \
     grep '^deb ' /etc/apt/sources.list | perl -pe 's/^deb/deb-src/' >> /etc/apt/sources.list; \
@@ -20,8 +26,8 @@ RUN if [ "$REL" = "buster" -o "$REL" = "bullseye" -o "$REL" = "bookworm" ]; then
     echo 'APT::Install-Suggests false;' >> /etc/apt/apt.conf
 
 RUN apt-get update
-RUN apt-get -y install fio liburing-dev libgoogle-perftools-dev devscripts
-RUN apt-get -y build-dep qemu
+RUN DEBIAN_FRONTEND=noninteractive TZ=Europe/Moscow apt-get -y install fio liburing-dev libgoogle-perftools-dev devscripts
+RUN DEBIAN_FRONTEND=noninteractive TZ=Europe/Moscow apt-get -y build-dep qemu
 # To build a custom version
 #RUN cp /root/packages/qemu-orig/* /root
 RUN apt-get --download-only source qemu
@@ -38,9 +44,9 @@ ADD src/client/qemu_driver.c /root/qemu_driver.c
 #    apt-get install -y vitastor-client vitastor-client-dev quilt
 
 RUN set -e; \
-    dpkg -i /root/packages/vitastor-$REL/vitastor-client_*.deb /root/packages/vitastor-$REL/vitastor-client-dev_*.deb; \
+    DEBIAN_FRONTEND=noninteractive TZ=Europe/Moscow apt-get -y install /root/packages/vitastor-$REL/vitastor-client_*.deb /root/packages/vitastor-$REL/vitastor-client-dev_*.deb; \
     apt-get update; \
-    apt-get install -y quilt; \
+    DEBIAN_FRONTEND=noninteractive TZ=Europe/Moscow apt-get -y install quilt; \
     mkdir -p /root/packages/qemu-$REL; \
     rm -rf /root/packages/qemu-$REL/*; \
     cd /root/packages/qemu-$REL; \
@@ -54,7 +60,7 @@ RUN set -e; \
     quilt add block/vitastor.c; \
     cp /root/qemu_driver.c block/vitastor.c; \
     quilt refresh; \
-    V=$(head -n1 debian/changelog | perl -pe 's/5\.2\+dfsg-9/5.2+dfsg-11/; s/^.*\((.*?)(~bpo[\d\+]*)?\).*$/$1/')+vitastor4; \
+    V=$(head -n1 debian/changelog | perl -pe 's/5\.2\+dfsg-9/5.2+dfsg-11/; s/^.*\((.*?)(\+deb\d+u\d+)?(~bpo[\d\+]*)?\).*$/$1/')+vitastor5; \
     if [ "$REL" = bullseye ]; then V=${V}bullseye; fi; \
     DEBEMAIL="Vitaliy Filippov <vitalif@yourcmc.ru>" dch -D $REL -v $V 'Plug Vitastor block driver'; \
     DEB_BUILD_OPTIONS=nocheck dpkg-buildpackage --jobs=auto -sa; \

debian/rules

@@ -4,6 +4,14 @@ export DH_VERBOSE = 1
 %:
 	dh $@
 
+override_dh_install:
+	perl -pe 's!prefix=/usr!prefix='`pwd`'/debian/tmp/usr!' < obj-x86_64-linux-gnu/src/client/vitastor.pc > node-binding/vitastor.pc
+	cd node-binding && PKG_CONFIG_PATH=./ PKG_CONFIG_ALLOW_SYSTEM_CFLAGS=1 npm install --unsafe-perm || exit 1
+	mkdir -p debian/tmp/usr/lib/x86_64-linux-gnu/nodejs/vitastor/build/Release
+	cp -v node-binding/package.json node-binding/index.js node-binding/addon.cc node-binding/addon.h node-binding/client.cc node-binding/client.h debian/tmp/usr/lib/x86_64-linux-gnu/nodejs/vitastor
+	cp -v node-binding/build/Release/addon.node debian/tmp/usr/lib/x86_64-linux-gnu/nodejs/vitastor/build/Release
+	dh_install
+
 override_dh_installdeb:
 	cat debian/fio_version >> debian/vitastor-fio.substvars
 	[ -f debian/qemu_version ] && (cat debian/qemu_version >> debian/vitastor-qemu.substvars) || true

debian/vitastor-opennebula.install

@@ -0,0 +1,3 @@
+opennebula/remotes var/lib/one/
+opennebula/sudoers.d etc/
+opennebula/install.sh var/lib/one/remotes/datastore/vitastor/

debian/vitastor-opennebula.postinst

@@ -0,0 +1,7 @@
+#!/bin/sh
+
+set -e
+
+if [ "$1" = "configure" ]; then
+	/var/lib/one/remotes/datastore/vitastor/install.sh
+fi

debian/vitastor-opennebula.triggers

@@ -0,0 +1,4 @@
+interest /var/lib/one/remotes/datastore/downloader.sh
+interest /etc/one/oned.conf
+interest /etc/one/vmm_exec/vmm_execrc
+interest /etc/apparmor.d/local/abstractions/libvirt-qemu

debian/vitastor.Dockerfile

@@ -21,10 +21,11 @@ RUN set -e -x; \
     echo 'APT::Install-Recommends false;' >> /etc/apt/apt.conf; \
     echo 'APT::Install-Suggests false;' >> /etc/apt/apt.conf
 
-RUN apt-get update
-RUN apt-get -y install fio liburing-dev libgoogle-perftools-dev devscripts libjerasure-dev cmake libibverbs-dev libisal-dev libnl-3-dev libnl-genl-3-dev curl
-RUN apt-get -y build-dep fio
-RUN apt-get --download-only source fio
+RUN apt-get update && \
+    apt-get -y install fio liburing-dev libgoogle-perftools-dev devscripts libjerasure-dev cmake \
+        libibverbs-dev librdmacm-dev libisal-dev libnl-3-dev libnl-genl-3-dev curl nodejs npm node-nan node-bindings && \
+    apt-get -y build-dep fio && \
+    apt-get --download-only source fio
 
 ADD . /root/vitastor
 RUN set -e -x; \

docker/Dockerfile

@@ -1,9 +1,11 @@
 # Build Docker image with Vitastor packages
 
-FROM debian:bullseye
+FROM debian:bookworm
 
-ADD vitastor.list /etc/apt/sources.list.d
-ADD vitastor.gpg /etc/apt/trusted.gpg.d
-ADD vitastor.pref /etc/apt/preferences.d
-ADD apt.conf /etc/apt/
-RUN apt-get update && apt-get -y install vitastor qemu-system-x86 qemu-system-common && apt-get clean
+ADD etc/apt /etc/apt/
+RUN apt-get update && apt-get -y install vitastor udev systemd qemu-system-x86 qemu-system-common qemu-block-extra qemu-utils jq nfs-common && apt-get clean
+ADD sleep.sh /usr/bin/
+ADD install.sh /usr/bin/
+ADD scripts /opt/scripts/
+ADD etc /etc/
+RUN ln -s /usr/lib/vitastor/mon/make-etcd /usr/bin/make-etcd

docker/Makefile

@@ -0,0 +1,9 @@
+VITASTOR_VERSION ?= v2.0.0
+
+all: build push
+
+build:
+	@docker build --rm -t vitalif/vitastor:$(VITASTOR_VERSION) .
+
+push:
+	@docker push vitalif/vitastor:$(VITASTOR_VERSION)

docker/etc/apt/sources.list.d/vitastor.list

@@ -0,0 +1 @@
+deb http://vitastor.io/debian bookworm main

docker/etc/systemd/system/vitastor-etcd.service

@@ -0,0 +1,27 @@
+[Unit]
+Description=Containerized etcd for Vitastor
+After=network-online.target local-fs.target time-sync.target docker.service vitastor-host.service
+Wants=network-online.target local-fs.target time-sync.target docker.service vitastor-host.service
+PartOf=vitastor.target
+
+[Service]
+Restart=always
+Environment=GOGC=50
+EnvironmentFile=/etc/vitastor/docker.conf
+EnvironmentFile=/etc/vitastor/etcd.conf
+SyslogIdentifier=etcd
+ExecStart=bash -c 'docker run --rm -i -v /var/lib/vitastor/etcd:/data \
+    --log-driver none --network host $CONTAINER_OPTIONS --name vitastor-etcd \
+    $ETCD_IMAGE /usr/local/bin/etcd --name "$ETCD_NAME" --data-dir /data \
+    --snapshot-count 10000 --advertise-client-urls http://$ETCD_IP:2379 --listen-client-urls http://$ETCD_IP:2379 \
+    --initial-advertise-peer-urls http://$ETCD_IP:2380 --listen-peer-urls http://$ETCD_IP:2380 \
+    --initial-cluster-token vitastor-etcd-1 --initial-cluster "$ETCD_INITIAL_CLUSTER" \
+    --initial-cluster-state new --max-txn-ops=100000 --max-request-bytes=104857600 \
+    --auto-compaction-retention=10 --auto-compaction-mode=revision'
+ExecStop=docker stop vitastor-etcd
+Restart=always
+StartLimitInterval=0
+RestartSec=10
+
+[Install]
+WantedBy=multi-user.target

docker/etc/systemd/system/vitastor-host.service

@@ -0,0 +1,23 @@
+[Unit]
+Description=Empty container for running Vitastor commands
+After=network-online.target local-fs.target time-sync.target docker.service
+Wants=network-online.target local-fs.target time-sync.target docker.service
+PartOf=vitastor.target
+
+[Service]
+Restart=always
+EnvironmentFile=/etc/vitastor/docker.conf
+ExecStart=bash -c 'docker run --rm -i -v /etc/vitastor:/etc/vitastor -v /dev:/dev -v /run:/run \
+    --security-opt seccomp=unconfined --privileged --pid=host --log-driver none --network host --name vitastor vitastor:$VITASTOR_VERSION \
+    sleep.sh'
+ExecStartPost=udevadm trigger
+ExecStop=docker stop vitastor
+WorkingDirectory=/
+PrivateTmp=false
+TasksMax=infinity
+Restart=always
+StartLimitInterval=0
+RestartSec=10
+
+[Install]
+WantedBy=multi-user.target

docker/etc/systemd/system/vitastor-mon.service

@@ -0,0 +1,23 @@
+[Unit]
+Description=Containerized Vitastor monitor
+After=network-online.target local-fs.target time-sync.target docker.service
+Wants=network-online.target local-fs.target time-sync.target docker.service
+PartOf=vitastor.target
+
+[Service]
+Restart=always
+EnvironmentFile=/etc/vitastor/docker.conf
+SyslogIdentifier=vitastor-mon
+ExecStart=bash -c 'docker run --rm -i -v /etc/vitastor:/etc/vitastor -v /var/lib/vitastor:/var/lib/vitastor -v /dev:/dev \
+    --log-driver none --network host $CONTAINER_OPTIONS --name vitastor-mon vitastor:$VITASTOR_VERSION \
+    node /usr/lib/vitastor/mon/mon-main.js'
+ExecStop=docker stop vitastor-mon
+WorkingDirectory=/
+PrivateTmp=false
+TasksMax=infinity
+Restart=always
+StartLimitInterval=0
+RestartSec=10
+
+[Install]
+WantedBy=multi-user.target

docker/etc/systemd/system/vitastor-osd@.service

@@ -0,0 +1,28 @@
+[Unit]
+Description=Containerized Vitastor object storage daemon osd.%i
+After=network-online.target local-fs.target time-sync.target docker.service vitastor-host.service
+Wants=network-online.target local-fs.target time-sync.target docker.service vitastor-host.service
+PartOf=vitastor.target
+
+[Service]
+LimitNOFILE=1048576
+LimitNPROC=1048576
+LimitMEMLOCK=infinity
+EnvironmentFile=/etc/vitastor/docker.conf
+SyslogIdentifier=vitastor-osd%i
+ExecStart=bash -c 'docker run --rm -i -v /etc/vitastor:/etc/vitastor -v /dev:/dev \
+    $(for i in $(ls /dev/vitastor/osd%i-*); do echo --device $i:$i; done) \
+    --log-driver none --network host --ulimit nofile=1048576 --ulimit memlock=-1 \
+    --security-opt seccomp=unconfined $CONTAINER_OPTIONS --name vitastor-osd%i \
+    vitastor:$VITASTOR_VERSION vitastor-disk exec-osd /dev/vitastor/osd%i-data'
+ExecStartPre=+docker exec vitastor vitastor-disk pre-exec /dev/vitastor/osd%i-data
+ExecStop=docker stop vitastor-etcd%i
+WorkingDirectory=/
+PrivateTmp=false
+TasksMax=infinity
+Restart=always
+StartLimitInterval=0
+RestartSec=10
+
+[Install]
+WantedBy=vitastor.target

docker/etc/systemd/system/vitastor.target

@@ -0,0 +1,4 @@
+[Unit]
+Description=vitastor target
+[Install]
+WantedBy=multi-user.target

docker/etc/udev/rules.d/90-vitastor.rules

@@ -0,0 +1,7 @@
+SUBSYSTEM=="block", ENV{ID_PART_ENTRY_TYPE}=="e7009fac-a5a1-4d72-af72-53de13059903", \
+    OWNER="vitastor", GROUP="vitastor", \
+    IMPORT{program}="/usr/bin/docker exec vitastor vitastor-disk udev $devnode", \
+    SYMLINK+="vitastor/$env{VITASTOR_ALIAS}"
+
+ENV{VITASTOR_OSD_NUM}!="", ACTION=="add", RUN{program}+="/usr/bin/systemctl enable --now --no-block vitastor-osd@$env{VITASTOR_OSD_NUM}"
+ENV{VITASTOR_OSD_NUM}!="", ACTION=="remove", RUN{program}+="/usr/bin/systemctl disable --now --no-block vitastor-osd@$env{VITASTOR_OSD_NUM}"

docker/etc/vitastor/docker.conf

@@ -0,0 +1,11 @@
+#
+# Configuration file for containerized Vitastor installation
+# (non-Kubernetes, with systemd and udev-based orchestration)
+#
+
+# Desired Vitastor version
+VITASTOR_VERSION=v2.0.0
+
+# Additional arguments for all containers
+# For example, you may want to specify a custom logging driver here
+CONTAINER_OPTIONS=""

docker/etc/vitastor/etcd.conf

@@ -0,0 +1,4 @@
+ETCD_IMAGE=quay.io/coreos/etcd:v3.5.18
+ETCD_NAME=""
+ETCD_IP=""
+ETCD_INITIAL_CLUSTER=""

docker/etc/vitastor/vitastor.conf

@@ -0,0 +1,2 @@
+{
+}

docker/install.sh

@@ -0,0 +1,9 @@
+#!/bin/bash
+
+set -e
+
+cp -urv /etc/default /host-etc/
+cp -urv /etc/systemd /host-etc/
+cp -urv /etc/udev /host-etc/
+cp -urnv /etc/vitastor /host-etc/
+cp -urnv /opt/scripts/* /host-bin/

docker/scripts/vitastor-cli

@@ -0,0 +1,3 @@
+#!/bin/bash
+
+docker exec -it vitastor vitastor-cli "$@"

docker/scripts/vitastor-disk

@@ -0,0 +1,3 @@
+#!/bin/bash
+
+docker exec -it vitastor vitastor-disk "$@"

docker/scripts/vitastor-fio

@@ -0,0 +1,3 @@
+#!/bin/bash
+
+docker exec -it vitastor fio "$@"

docker/scripts/vitastor-nbd

@@ -0,0 +1,3 @@
+#!/bin/bash
+
+docker exec -it vitastor vitastor-nbd "$@"

docker/sleep.sh

@@ -0,0 +1,3 @@
+#!/bin/bash
+
+while :; do sleep infinity; done

docker/vitastor.list

@@ -1 +0,0 @@
-deb http://vitastor.io/debian bullseye main

docs/config.en.md

@@ -13,7 +13,7 @@ Vitastor configuration consists of:
 - [Separate OSD settings](config/pool.en.md#osd-settings)
 - [Inode configuration](config/inode.en.md) i.e. image metadata like name, size and parent reference
 
-Configuration parameters can be set in 3 places:
+Configuration parameters can be set in 4 places:
 - Configuration file (`/etc/vitastor/vitastor.conf` or other path)
 - etcd key `/vitastor/config/global`. Most variables can be set there, but etcd
   connection parameters should obviously be set in the configuration file.

docs/config.ru.md

@@ -14,7 +14,7 @@
 - [Настроек инодов](config/inode.ru.md), т.е. метаданных образов, таких, как имя, размер и ссылки на
   родительский образ
 
-Параметры конфигурации могут задаваться в 3 местах:
+Параметры конфигурации могут задаваться в 4 местах:
 - Файле конфигурации (`/etc/vitastor/vitastor.conf` или по другому пути)
 - Ключе в etcd `/vitastor/config/global`. Большая часть параметров может
   задаваться там, кроме, естественно, самих параметров соединения с etcd,

docs/config/client.en.md

@@ -13,6 +13,7 @@ affect their interaction with the cluster.
 - [client_retry_interval](#client_retry_interval)
 - [client_eio_retry_interval](#client_eio_retry_interval)
 - [client_retry_enospc](#client_retry_enospc)
+- [client_wait_up_timeout](#client_wait_up_timeout)
 - [client_max_dirty_bytes](#client_max_dirty_bytes)
 - [client_max_dirty_ops](#client_max_dirty_ops)
 - [client_enable_writeback](#client_enable_writeback)
@@ -70,6 +71,19 @@ and clients are not blocked and just get EIO error code instead.
 Retry writes on out of space errors to wait until some space is freed on
 OSDs.
 
+## client_wait_up_timeout
+
+- Type: seconds
+- Default: 16
+- Can be changed online: yes
+
+Wait for this number of seconds until PGs are up when doing operations
+which require all PGs to be up. Currently only used by object listings
+in delete and merge-based commands ([vitastor-cli rm](../usage/cli.en.md#rm), merge and so on).
+
+The default value is calculated as `1 + OSD lease timeout`, which is
+`1 + etcd_report_interval + max_etcd_attempts*2*etcd_quick_timeout`.
+
 ## client_max_dirty_bytes
 
 - Type: integer

docs/config/client.ru.md

@@ -13,6 +13,7 @@
 - [client_retry_interval](#client_retry_interval)
 - [client_eio_retry_interval](#client_eio_retry_interval)
 - [client_retry_enospc](#client_retry_enospc)
+- [client_wait_up_timeout](#client_wait_up_timeout)
 - [client_max_dirty_bytes](#client_max_dirty_bytes)
 - [client_max_dirty_ops](#client_max_dirty_ops)
 - [client_enable_writeback](#client_enable_writeback)
@@ -72,6 +73,19 @@ RDMA и хотите повысить пиковую производитель
 Повторять запросы записи, завершившиеся с ошибками нехватки места, т.е.
 ожидать, пока на OSD не освободится место.
 
+## client_wait_up_timeout
+
+- Тип: секунды
+- Значение по умолчанию: 16
+- Можно менять на лету: да
+
+Время ожидания поднятия PG при операциях, требующих активности всех PG.
+В данный момент используется листингами объектов в командах, использующих
+удаление и слияние ([vitastor-cli rm](../usage/cli.ru.md#rm), merge и подобные).
+
+Значение по умолчанию вычисляется как `1 + время lease OSD`, равное
+`1 + etcd_report_interval + max_etcd_attempts*2*etcd_quick_timeout`.
+
 ## client_max_dirty_bytes
 
 - Тип: целое число

docs/config/layout-cluster.en.md

@@ -106,8 +106,8 @@ SSD cache or "media-cache" - for example, a lot of Seagate EXOS drives have
 it (they have internal SSD cache even though it's not stated in datasheets).
 
 Setting this parameter to "all" or "small" in OSD parameters requires enabling
-[disable_journal_fsync](layout-osd.en.yml#disable_journal_fsync) and
-[disable_meta_fsync](layout-osd.en.yml#disable_meta_fsync), setting it to
-"all" also requires enabling [disable_data_fsync](layout-osd.en.yml#disable_data_fsync).
+[disable_journal_fsync](layout-osd.en.md#disable_journal_fsync) and
+[disable_meta_fsync](layout-osd.en.md#disable_meta_fsync), setting it to
+"all" also requires enabling [disable_data_fsync](layout-osd.en.md#disable_data_fsync).
 vitastor-disk tried to do that by default, first checking/disabling drive cache.
 If it can't disable drive cache, OSD get initialized with "none".

docs/config/layout-cluster.ru.md

@@ -112,6 +112,6 @@ HDD-дисках с внутренним SSD или "медиа" кэшем - н
 указано в спецификациях).
 
 Указание "all" или "small" в настройках / командной строке OSD требует
-включения [disable_journal_fsync](layout-osd.ru.yml#disable_journal_fsync) и
-[disable_meta_fsync](layout-osd.ru.yml#disable_meta_fsync), значение "all"
-также требует включения [disable_data_fsync](layout-osd.ru.yml#disable_data_fsync).
+включения [disable_journal_fsync](layout-osd.ru.md#disable_journal_fsync) и
+[disable_meta_fsync](layout-osd.ru.md#disable_meta_fsync), значение "all"
+также требует включения [disable_data_fsync](layout-osd.ru.md#disable_data_fsync).

docs/config/layout-osd.en.md

@@ -118,12 +118,13 @@ Physical block size of the journal device. Must be a multiple of
 - Type: boolean
 - Default: false
 
-Do not issue fsyncs to the data device, i.e. do not flush its cache.
-Safe ONLY if your data device has write-through cache. If you disable
-the cache yourself using `hdparm` or `scsi_disk/cache_type` then make sure
-that the cache disable command is run every time before starting Vitastor
-OSD, for example, in the systemd unit. See also `immediate_commit` option
-for the instructions to disable cache and how to benefit from it.
+Do not issue fsyncs to the data device, i.e. do not force it to flush cache.
+Safe ONLY if your data device has write-through cache or if write-back
+cache is disabled. If you disable drive cache manually with `hdparm` or
+writing to `/sys/.../scsi_disk/cache_type` then make sure that you do it
+every time before starting Vitastor OSD (vitastor-disk does it automatically).
+See also [immediate_commit](layout-cluster.en.md#immediate_commit)
+for information about how to benefit from disabled cache.
 
 ## disable_meta_fsync
 
@@ -171,8 +172,7 @@ size, it actually has to write the whole 4 KB sector.
 
 Because of this it can actually be beneficial to use SSDs which work well
 with 512 byte sectors and use 512 byte disk_alignment, journal_block_size
-and meta_block_size. But the only SSD that may fit into this category is
-Intel Optane (probably, not tested yet).
+and meta_block_size. But at the moment, no such SSDs are known...
 
 Clients don't need to be aware of disk_alignment, so it's not required to
 put a modified value into etcd key /vitastor/config/global.

docs/config/layout-osd.ru.md

@@ -122,13 +122,14 @@ SSD-диске, иначе производительность пострада
 - Тип: булево (да/нет)
 - Значение по умолчанию: false
 
-Не отправлять fsync-и устройству данных, т.е. не сбрасывать его кэш.
+Не отправлять fsync-и устройству данных, т.е. не заставлять его сбрасывать кэш.
 Безопасно, ТОЛЬКО если ваше устройство данных имеет кэш со сквозной
-записью (write-through). Если вы отключаете кэш через `hdparm` или
-`scsi_disk/cache_type`, то удостоверьтесь, что команда отключения кэша
-выполняется перед каждым запуском Vitastor OSD, например, в systemd unit-е.
-Смотрите также опцию `immediate_commit` для инструкций по отключению кэша
-и о том, как из этого извлечь выгоду.
+записью (write-through) или если кэш с отложенной записью (write-back) отключён.
+Если вы отключаете кэш вручную через `hdparm` или запись в `/sys/.../scsi_disk/cache_type`,
+то удостоверьтесь, что вы делаете это каждый раз перед запуском Vitastor OSD
+(vitastor-disk делает это автоматически). Смотрите также опцию
+[immediate_commit](layout-cluster.ru.md#immediate_commit) для информации о том,
+как извлечь выгоду из отключённого кэша.
 
 ## disable_meta_fsync
 
@@ -179,9 +180,8 @@ SSD и HDD диски используют 4 КБ физические сект
 
 Поэтому, на самом деле, может быть выгодно найти SSD, хорошо работающие с
 меньшими, 512-байтными, блоками и использовать 512-байтные disk_alignment,
-journal_block_size и meta_block_size. Однако единственные SSD, которые
-теоретически могут попасть в эту категорию - это Intel Optane (но и это
-пока не проверялось автором).
+journal_block_size и meta_block_size. Однако на данный момент такие SSD
+не известны...
 
 Клиентам не обязательно знать про disk_alignment, так что помещать значение
 этого параметра в etcd в /vitastor/config/global не нужно.

docs/config/monitor.en.md

@@ -24,6 +24,7 @@ These parameters only apply to Monitors.
 - [osd_out_time](#osd_out_time)
 - [placement_levels](#placement_levels)
 - [use_old_pg_combinator](#use_old_pg_combinator)
+- [osd_backfillfull_ratio](#osd_backfillfull_ratio)
 
 ## use_antietcd
 
@@ -175,3 +176,18 @@ present in the configuration, then it is defined with the default priority
 
 Use the old PG combination generator which doesn't support [level_placement](pool.en.md#level_placement)
 and [raw_placement](pool.en.md#raw_placement) for pools which don't use this features.
+
+## osd_backfillfull_ratio
+
+- Type: number
+- Default: 0.99
+
+Monitors try to prevent OSDs becoming 100% full during rebalance or recovery by
+calculating how much space will be occupied on every OSD after all rebalance
+and recovery operations finish, and pausing rebalance and recovery if that
+amount of space exceeds OSD capacity multiplied by the value of this
+configuration parameter.
+
+Future used space is calculated by summing space used by all user data blocks
+(objects) in all PGs placed on a specific OSD, even if some of these objects
+currently reside on a different set of OSDs.

docs/config/monitor.ru.md

@@ -24,6 +24,7 @@
 - [osd_out_time](#osd_out_time)
 - [placement_levels](#placement_levels)
 - [use_old_pg_combinator](#use_old_pg_combinator)
+- [osd_backfillfull_ratio](#osd_backfillfull_ratio)
 
 ## use_antietcd
 
@@ -178,3 +179,19 @@ OSD перед обновлением агрегированной статис
 
 Использовать старый генератор комбинаций PG, не поддерживающий [level_placement](pool.ru.md#level_placement)
 и [raw_placement](pool.ru.md#raw_placement) для пулов, которые не используют данные функции.
+
+## osd_backfillfull_ratio
+
+- Тип: число
+- Значение по умолчанию: 0.99
+
+Мониторы стараются предотвратить 100% заполнение OSD в процессе ребаланса
+или восстановления, рассчитывая, сколько места будет занято на каждом OSD после
+завершения всех операций ребаланса и восстановления, и приостанавливая
+ребаланс и восстановление, если рассчитанный объём превышает ёмкость OSD,
+умноженную на значение данного параметра.
+
+Будущее занятое место рассчитывается сложением места, занятого всеми
+пользовательскими блоками данных (объектами) во всех PG, расположенных
+на конкретном OSD, даже если часть этих объектов в данный момент находится
+на другом наборе OSD.

docs/config/network.en.md

@@ -30,6 +30,7 @@ between clients, OSDs and etcd.
 - [etcd_slow_timeout](#etcd_slow_timeout)
 - [etcd_keepalive_timeout](#etcd_keepalive_timeout)
 - [etcd_ws_keepalive_interval](#etcd_ws_keepalive_interval)
+- [etcd_min_reload_interval](#etcd_min_reload_interval)
 
 ## tcp_header_buffer_size
 
@@ -68,11 +69,17 @@ but they are not connected to the cluster.
 - Type: string
 
 RDMA device name to use for Vitastor OSD communications (for example,
-"rocep5s0f0"). Now Vitastor supports all adapters, even ones without
-ODP support, like Mellanox ConnectX-3 and non-Mellanox cards.
+"rocep5s0f0"). If not specified, Vitastor will try to find an RoCE
+device matching [osd_network](osd.en.md#osd_network), preferring RoCEv2,
+or choose the first available RDMA device if no RoCE devices are
+found or if `osd_network` is not specified. Auto-selection is also
+unsupported with old libibverbs < v32, like in Debian 10 Buster or
+CentOS 7.
 
-Versions up to Vitastor 1.2.0 required ODP which is only present in
-Mellanox ConnectX >= 4. See also [rdma_odp](#rdma_odp).
+Vitastor supports all adapters, even ones without ODP support, like
+Mellanox ConnectX-3 and non-Mellanox cards. Versions up to Vitastor
+1.2.0 required ODP which is only present in Mellanox ConnectX >= 4.
+See also [rdma_odp](#rdma_odp).
 
 Run `ibv_devinfo -v` as root to list available RDMA devices and their
 features.
@@ -95,15 +102,17 @@ your device has.
 ## rdma_gid_index
 
 - Type: integer
-- Default: 0
 
 Global address identifier index of the RDMA device to use. Different GID
 indexes may correspond to different protocols like RoCEv1, RoCEv2 and iWARP.
 Search for "GID" in `ibv_devinfo -v` output to determine which GID index
 you need.
 
-**IMPORTANT:** If you want to use RoCEv2 (as recommended) then the correct
-rdma_gid_index is usually 1 (IPv6) or 3 (IPv4).
+If not specified, Vitastor will try to auto-select a RoCEv2 IPv4 GID, then
+RoCEv2 IPv6 GID, then RoCEv1 IPv4 GID, then RoCEv1 IPv6 GID, then IB GID.
+GID auto-selection is unsupported with libibverbs < v32.
+
+A correct rdma_gid_index for RoCEv2 is usually 1 (IPv6) or 3 (IPv4).
 
 ## rdma_mtu
 
@@ -253,3 +262,13 @@ etcd_report_interval to guarantee that keepalive actually works.
 
 etcd websocket ping interval required to keep the connection alive and
 detect disconnections quickly.
+
+## etcd_min_reload_interval
+
+- Type: milliseconds
+- Default: 1000
+- Can be changed online: yes
+
+Minimum interval for full etcd state reload. Introduced to prevent
+excessive load on etcd during outages when etcd can't keep up with event
+streams and cancels them.

docs/config/network.ru.md

@@ -30,6 +30,7 @@
 - [etcd_slow_timeout](#etcd_slow_timeout)
 - [etcd_keepalive_timeout](#etcd_keepalive_timeout)
 - [etcd_ws_keepalive_interval](#etcd_ws_keepalive_interval)
+- [etcd_min_reload_interval](#etcd_min_reload_interval)
 
 ## tcp_header_buffer_size
 
@@ -71,12 +72,17 @@ RDMA может быть нужно только если у клиентов е
 - Тип: строка
 
 Название RDMA-устройства для связи с Vitastor OSD (например, "rocep5s0f0").
-Сейчас Vitastor поддерживает все модели адаптеров, включая те, у которых
-нет поддержки ODP, то есть вы можете использовать RDMA с ConnectX-3 и
-картами производства не Mellanox.
+Если не указано, Vitastor попробует найти RoCE-устройство, соответствующее
+[osd_network](osd.en.md#osd_network), предпочитая RoCEv2, или выбрать первое
+попавшееся RDMA-устройство, если RoCE-устройств нет или если сеть `osd_network`
+не задана. Также автовыбор не поддерживается со старыми версиями библиотеки
+libibverbs < v32, например в Debian 10 Buster или CentOS 7.
 
-Версии Vitastor до 1.2.0 включительно требовали ODP, который есть только
-на Mellanox ConnectX 4 и более новых. См. также [rdma_odp](#rdma_odp).
+Vitastor поддерживает все модели адаптеров, включая те, у которых
+нет поддержки ODP, то есть вы можете использовать RDMA с ConnectX-3 и
+картами производства не Mellanox. Версии Vitastor до 1.2.0 включительно
+требовали ODP, который есть только на Mellanox ConnectX 4 и более новых.
+См. также [rdma_odp](#rdma_odp).
 
 Запустите `ibv_devinfo -v` от имени суперпользователя, чтобы посмотреть
 список доступных RDMA-устройств, их параметры и возможности.
@@ -101,15 +107,18 @@ Control) и ECN (Explicit Congestion Notification).
 ## rdma_gid_index
 
 - Тип: целое число
-- Значение по умолчанию: 0
 
 Номер глобального идентификатора адреса RDMA-устройства, который следует
 использовать. Разным gid_index могут соответствовать разные протоколы связи:
 RoCEv1, RoCEv2, iWARP. Чтобы понять, какой нужен вам - смотрите строчки со
 словом "GID" в выводе команды `ibv_devinfo -v`.
 
-**ВАЖНО:** Если вы хотите использовать RoCEv2 (как мы и рекомендуем), то
-правильный rdma_gid_index, как правило, 1 (IPv6) или 3 (IPv4).
+Если не указан, Vitastor попробует автоматически выбрать сначала GID,
+соответствующий RoCEv2 IPv4, потом RoCEv2 IPv6, потом RoCEv1 IPv4, потом
+RoCEv1 IPv6, потом IB. Авто-выбор GID не поддерживается со старыми версиями
+libibverbs < v32.
+
+Правильный rdma_gid_index для RoCEv2, как правило, 1 (IPv6) или 3 (IPv4).
 
 ## rdma_mtu
 
@@ -263,3 +272,13 @@ etcd_report_interval, чтобы keepalive гарантированно рабо
 - Можно менять на лету: да
 
 Интервал проверки живости вебсокет-подключений к etcd.
+
+## etcd_min_reload_interval
+
+- Тип: миллисекунды
+- Значение по умолчанию: 1000
+- Можно менять на лету: да
+
+Минимальный интервал полной перезагрузки состояния из etcd. Добавлено для
+предотвращения избыточной нагрузки на etcd во время отказов, когда etcd не
+успевает рассылать потоки событий и отменяет их.

docs/config/osd.en.md

@@ -7,8 +7,8 @@
 # Runtime OSD Parameters
 
 These parameters only apply to OSDs, are not fixed at the moment of OSD drive
-initialization and can be changed - either with an OSD restart or, for some of
-them, even without restarting by updating configuration in etcd.
+initialization and can be changed - in /etc/vitastor/vitastor.conf or [vitastor-disk update-sb](../usage/disk.en.md#update-sb)
+with an OSD restart or, for some of them, even without restarting by updating configuration in etcd.
 
 - [osd_iothread_count](#osd_iothread_count)
 - [etcd_report_interval](#etcd_report_interval)
@@ -61,6 +61,9 @@ them, even without restarting by updating configuration in etcd.
 - [recovery_tune_agg_interval](#recovery_tune_agg_interval)
 - [recovery_tune_sleep_min_us](#recovery_tune_sleep_min_us)
 - [recovery_tune_sleep_cutoff_us](#recovery_tune_sleep_cutoff_us)
+- [discard_on_start](#discard_on_start)
+- [min_discard_size](#min_discard_size)
+- [allow_net_split](#allow_net_split)
 
 ## osd_iothread_count
 
@@ -316,7 +319,7 @@ for hot data and slower disks - HDDs and maybe SATA SSDs - but will slightly
 decrease write performance for fast disks because page cache is an overhead
 itself.
 
-Choose "directsync" to use [immediate_commit](layout-cluster.ru.md#immediate_commit)
+Choose "directsync" to use [immediate_commit](layout-cluster.en.md#immediate_commit)
 (which requires disable_data_fsync) with drives having write-back cache
 which can't be turned off, for example, Intel Optane. Also note that *some*
 desktop SSDs (for example, HP EX950) may ignore O_SYNC thus making
@@ -629,3 +632,30 @@ are changed to 0.
 
 Maximum possible value for auto-tuned recovery_sleep_us. Higher values
 are treated as outliers and ignored in aggregation.
+
+## discard_on_start
+
+- Type: boolean
+
+Discard (SSD TRIM) unused data device blocks on every OSD startup.
+
+## min_discard_size
+
+- Type: integer
+- Default: 1048576
+
+Minimum consecutive block size to TRIM it.
+
+## allow_net_split
+
+- Type: boolean
+- Default: false
+
+Allow "safe" cases of network splits/partitions - allow to start PGs without
+connections to some OSDs currently registered as alive in etcd, if the number
+of actually connected PG OSDs is at least pg_minsize. That is, allow some OSDs to lose
+connectivity with some other OSDs as long as it doesn't break pg_minsize guarantees.
+The downside is that it increases the probability of writing data into just pg_minsize
+OSDs during failover which can lead to PGs becoming incomplete after additional outages.
+
+The old behaviour in versions up to 2.0.0 was equal to enabled allow_net_split.

docs/config/osd.ru.md

@@ -8,8 +8,8 @@
 
 Данные параметры используются только OSD, но, в отличие от дисковых параметров,
 не фиксируются в момент инициализации дисков OSD и могут быть изменены в любой
-момент с помощью перезапуска OSD, а некоторые и без перезапуска, с помощью
-изменения конфигурации в etcd.
+момент с перезапуском OSD в /etc/vitastor/vitastor.conf или [vitastor-disk update-sb](../usage/disk.ru.md#update-sb),
+а некоторые и без перезапуска, с помощью изменения конфигурации в etcd.
 
 - [osd_iothread_count](#osd_iothread_count)
 - [etcd_report_interval](#etcd_report_interval)
@@ -62,6 +62,9 @@
 - [recovery_tune_agg_interval](#recovery_tune_agg_interval)
 - [recovery_tune_sleep_min_us](#recovery_tune_sleep_min_us)
 - [recovery_tune_sleep_cutoff_us](#recovery_tune_sleep_cutoff_us)
+- [discard_on_start](#discard_on_start)
+- [min_discard_size](#min_discard_size)
+- [allow_net_split](#allow_net_split)
 
 ## osd_iothread_count
 
@@ -660,3 +663,31 @@ EC (кодов коррекции ошибок) с более, чем 1 диск
 Максимальное возможное значение авто-подстроенного recovery_sleep_us.
 Большие значения считаются случайными выбросами и игнорируются в
 усреднении.
+
+## discard_on_start
+
+- Тип: булево (да/нет)
+
+Освобождать (SSD TRIM) неиспользуемые блоки диска данных при каждом запуске OSD.
+
+## min_discard_size
+
+- Тип: целое число
+- Значение по умолчанию: 1048576
+
+Минимальный размер последовательного блока данных, чтобы освобождать его через TRIM.
+
+## allow_net_split
+
+- Тип: булево (да/нет)
+- Значение по умолчанию: false
+
+Разрешить "безопасные" случаи разделений сети - разрешить активировать PG без
+соединений к некоторым OSD, помеченным активными в etcd, если общее число активных
+OSD в PG составляет как минимум pg_minsize. То есть, разрешать некоторым OSD терять
+соединения с некоторыми другими OSD, если это не нарушает гарантий pg_minsize.
+Минус такого разрешения в том, что оно повышает вероятность записи данных ровно в
+pg_minsize OSD во время переключений, что может потом привести к тому, что PG станут
+неполными (incomplete), если упадут ещё какие-то OSD.
+
+Старое поведение в версиях до 2.0.0 было идентично включённому allow_net_split.

docs/config/pool.en.md

@@ -43,7 +43,7 @@ Parameters:
 - [osd_tags](#osd_tags)
 - [primary_affinity_tags](#primary_affinity_tags)
 - [scrub_interval](#scrub_interval)
-- [used_for_fs](#used_for_fs)
+- [used_for_app](#used_for_app)
 
 Examples:
 
@@ -55,7 +55,7 @@ Examples:
 OSD placement tree is set in a separate etcd key `/vitastor/config/node_placement`
 in the following JSON format:
 
-`
+```
 {
   "<node name or OSD number>": {
     "level": "<level>",
@@ -63,7 +63,7 @@ in the following JSON format:
   },
   ...
 }
-`
+```
 
 Here, if a node name is a number then it is assumed to refer to an OSD.
 Level of the OSD is always "osd" and cannot be overriden. You may only
@@ -189,6 +189,9 @@ So, pg_minsize regulates the number of failures that a pool can tolerate
 without temporary downtime for [osd_out_time](monitor.en.md#osd_out_time),
 but at a cost of slightly reduced storage reliability.
 
+See also [allow_net_split](osd.en.md#allow_net_split) and
+[PG state descriptions](../usage/admin.en.md#pg-states).
+
 FIXME: pg_minsize behaviour may be changed in the future to only make PGs
 read-only instead of deactivating them.
 
@@ -377,24 +380,37 @@ of the OSDs containing a data chunk for a PG.
 Automatic scrubbing interval for this pool. Overrides
 [global scrub_interval setting](osd.en.md#scrub_interval).
 
-## used_for_fs
+## used_for_app
 
 - Type: string
 
-If non-empty, the pool is marked as used for VitastorFS with metadata stored
-in block image (regular Vitastor volume) named as the value of this pool parameter.
+If non-empty, the pool is marked as used for a separate application, for example,
+VitastorFS or S3, which allocates Vitastor volume IDs by itself and does not use
+image/inode metadata in etcd.
 
-When a pool is marked as used for VitastorFS, regular block volume creation in it
+When a pool is marked as used for such app, regular block volume creation in it
 is disabled (vitastor-cli refuses to create images without --force) to protect
-the user from block volume and FS file ID collisions and data loss.
+the user from block volume and FS/S3 volume ID collisions and data loss.
 
-[vitastor-nfs](../usage/nfs.ru.md), in its turn, refuses to use pools not marked
+Also such pools do not calculate per-inode space usage statistics in etcd because
+using it for an external application implies that it may contain a very large
+number of volumes and their statistics may take too much space in etcd.
+
+Setting used_for_app to `fs:<name>` tells Vitastor that the pool is used for VitastorFS
+with VitastorKV metadata base stored in a block image (regular Vitastor volume) named
+`<name>`.
+
+[vitastor-nfs](../usage/nfs.en.md), in its turn, refuses to use pools not marked
 for the corresponding FS when starting. This also implies that you can use one
 pool only for one VitastorFS.
 
-The second thing that is disabled for VitastorFS pools is reporting per-inode space
-usage statistics in etcd because a FS pool may store a very large number of files
-and statistics for them all would take a lot of space in etcd.
+If you plan to use the pool for S3, set its used_for_app to `s3:<name>`. `<name>` may
+be basically anything you want (for example, `s3:standard`) - it's not validated
+by Vitastor S3 components in any way.
+
+All other values except prefixed with `fs:` or `s3:` may be used freely and don't
+mean anything special for Vitastor core components. For now, you can use them as
+you wish.
 
 # Examples
 

docs/config/pool.ru.md

@@ -42,7 +42,7 @@
 - [osd_tags](#osd_tags)
 - [primary_affinity_tags](#primary_affinity_tags)
 - [scrub_interval](#scrub_interval)
-- [used_for_fs](#used_for_fs)
+- [used_for_app](#used_for_app)
 
 Примеры:
 
@@ -54,7 +54,7 @@
 Дерево размещения OSD задаётся в отдельном ключе etcd `/vitastor/config/node_placement`
 в следующем JSON-формате:
 
-`
+```
 {
   "<имя узла или номер OSD>": {
     "level": "<уровень>",
@@ -62,7 +62,7 @@
   },
   ...
 }
-`
+```
 
 Здесь, если название узла - число, считается, что это OSD. Уровень OSD
 всегда равен "osd" и не может быть переопределён. Для OSD вы можете только
@@ -256,7 +256,7 @@ PG в Vitastor эферемерны, то есть вы можете менят
 
 ## raw_placement
 
-- Type: string
+- Тип: строка
 
 Низкоуровневые правила генерации PG в форме DSL (доменно-специфичного языка).
 Используйте, только если действительно знаете, зачем вам это надо :)
@@ -383,26 +383,42 @@ OSD с "all".
 Интервал скраба, то есть, автоматической фоновой проверки данных для данного пула.
 Переопределяет [глобальную настройку scrub_interval](osd.ru.md#scrub_interval).
 
-## used_for_fs
+## used_for_app
 
-- Type: string
+- Тип: строка
 
-Если непусто, пул помечается как используемый для файловой системы VitastorFS с
-метаданными, хранимыми в блочном образе Vitastor с именем, равным значению
-этого параметра.
+Если непусто, пул помечается как используемый для отдельного приложения, например,
+для VitastorFS или S3, которое распределяет ID образов в пуле само и не использует
+метаданные образов/инодов в etcd.
 
-Когда пул помечается как используемый для VitastorFS, создание обычных блочных
-образов в нём отключается (vitastor-cli отказывается создавать образы без --force),
-чтобы защитить пользователя от коллизий ID файлов и блочных образов и, таким
-образом, от потери данных.
+Когда пул помечается используемым для такого приложения, создание обычных блочных
+образов в нём запрещается (vitastor-cli отказывается создавать образы без --force),
+чтобы защитить пользователя от коллизий ID блочных образов и томов ФС/S3, и,
+таким образом, от потери данных.
+
+Также для таких пулов отключается передача статистики в etcd по отдельным инодам,
+так как использование для внешнего приложения подразумевает, что пул может содержать
+очень много томов и их статистика может занять слишком много места в etcd.
+
+Установка used_for_app в значение `fs:<name>` сообщает о том, что пул используется
+для VitastorFS с базой метаданных VitastorKV, хранимой в блочном образе с именем
+`<name>`.
 
 [vitastor-nfs](../usage/nfs.ru.md), в свою очередь, при запуске отказывается
-использовать для ФС пулы, не выделенные для неё. Это также означает, что один
-пул может использоваться только для одной VitastorFS.
+использовать для ФС пулы, не помеченные, как используемые для неё. Это также
+означает, что один пул может использоваться только для одной VitastorFS.
 
-Также для ФС-пулов отключается передача статистики в etcd по отдельным инодам,
-так как ФС-пул может содержать очень много файлов и статистика по ним всем
-заняла бы очень много места в etcd.
+Если же вы планируете использовать пул для данных S3, установите его used_for_app
+в значение `s3:<name>`, где `<name>` - любое название по вашему усмотрению
+(например, `s3:standard`) - конкретное содержимое `<name>` пока никак не проверяется
+компонентами Vitastor S3.
+
+Смотрите также [allow_net_split](osd.ru.md#allow_net_split) и
+[документацию по состояниям PG](../usage/admin.ru.md#состояния-pg).
+
+Все остальные значения used_for_app, кроме начинающихся на `fs:` или `s3:`, не
+означают ничего особенного для основных компонентов Vitastor. Поэтому сейчас вы
+можете использовать их свободно любым желаемым способом.
 
 # Примеры
 

docs/config/src/client.yml

@@ -61,6 +61,24 @@
   info_ru: |
     Повторять запросы записи, завершившиеся с ошибками нехватки места, т.е.
     ожидать, пока на OSD не освободится место.
+- name: client_wait_up_timeout
+  type: sec
+  default: 16
+  online: true
+  info: |
+    Wait for this number of seconds until PGs are up when doing operations
+    which require all PGs to be up. Currently only used by object listings
+    in delete and merge-based commands ([vitastor-cli rm](../usage/cli.en.md#rm), merge and so on).
+
+    The default value is calculated as `1 + OSD lease timeout`, which is
+    `1 + etcd_report_interval + max_etcd_attempts*2*etcd_quick_timeout`.
+  info_ru: |
+    Время ожидания поднятия PG при операциях, требующих активности всех PG.
+    В данный момент используется листингами объектов в командах, использующих
+    удаление и слияние ([vitastor-cli rm](../usage/cli.ru.md#rm), merge и подобные).
+
+    Значение по умолчанию вычисляется как `1 + время lease OSD`, равное
+    `1 + etcd_report_interval + max_etcd_attempts*2*etcd_quick_timeout`.
 - name: client_max_dirty_bytes
   type: int
   default: 33554432

docs/config/src/included.en.md

@@ -14,8 +14,12 @@
 
 {{../../installation/packages.en.md}}
 
+{{../../installation/docker.en.md}}
+
 {{../../installation/proxmox.en.md}}
 
+{{../../installation/opennebula.en.md}}
+
 {{../../installation/openstack.en.md}}
 
 {{../../installation/kubernetes.en.md}}

docs/config/src/included.ru.md

@@ -14,8 +14,12 @@
 
 {{../../installation/packages.ru.md}}
 
+{{../../installation/docker.ru.md}}
+
 {{../../installation/proxmox.ru.md}}
 
+{{../../installation/opennebula.ru.md}}
+
 {{../../installation/openstack.ru.md}}
 
 {{../../installation/kubernetes.ru.md}}

docs/config/src/layout-cluster.yml

@@ -97,9 +97,9 @@
     it (they have internal SSD cache even though it's not stated in datasheets).
 
     Setting this parameter to "all" or "small" in OSD parameters requires enabling
-    [disable_journal_fsync](layout-osd.en.yml#disable_journal_fsync) and
-    [disable_meta_fsync](layout-osd.en.yml#disable_meta_fsync), setting it to
-    "all" also requires enabling [disable_data_fsync](layout-osd.en.yml#disable_data_fsync).
+    [disable_journal_fsync](layout-osd.en.md#disable_journal_fsync) and
+    [disable_meta_fsync](layout-osd.en.md#disable_meta_fsync), setting it to
+    "all" also requires enabling [disable_data_fsync](layout-osd.en.md#disable_data_fsync).
     vitastor-disk tried to do that by default, first checking/disabling drive cache.
     If it can't disable drive cache, OSD get initialized with "none".
   info_ru: |
@@ -156,6 +156,6 @@
     указано в спецификациях).
 
     Указание "all" или "small" в настройках / командной строке OSD требует
-    включения [disable_journal_fsync](layout-osd.ru.yml#disable_journal_fsync) и
-    [disable_meta_fsync](layout-osd.ru.yml#disable_meta_fsync), значение "all"